Description:TECHNICAL FIELD
The present disclosure generally relates to loan servicing platforms, and more particularly relates to a system and method for processing customer requests in loan servicing platforms.
BACKGROUND
Before the advent of digital technologies, loan servicing operated through manual, paper-based processes. Lenders handled loans using physical documents, engaging in time-consuming tasks such as payment processing and record-keeping, which were prone to errors. The emergence of digital technologies brought about loan servicing platforms, addressing the limitations of traditional approaches. These platforms automate various loan-related tasks, including managing partner data, handling customer loan requests, and collecting payments (principal, interest, and/or escrow) from customers.
However, existing loan servicing platforms struggle to efficiently manage partner resources. For example, when high-risk loan requests come in, these platforms attempt to assign them to a specific partner willing to take on the associated risk. This results in some partners being over-utilized while others are under-utilized. Consequently, there is a pressing need for a technical and reliable solution that can effectively manage partner resources.
SUMMARY
Various embodiments of the present disclosure provide a system and a method for processing customer requests in a loan servicing platform, such that resources of the partners are utilized in an efficient manner.
In one aspect of the present disclosure, a system is provided. The system comprises a memory configured to store computer-executable instructions, and a processor communicatively coupled to the memory. The processor is configured to execute the computer-executable instructions to acquire partner data associated with a plurality of partners. The acquired partner data includes risk information associated with at least one customer segment of the plurality of customers. Further, the processor acquires first disbursed data associated with the plurality of partners for the at least one customer segment and computes a plurality of weights for the at least one customer segment based on the acquired partner data and the acquired first disbursed data. Each weight of the computed plurality of weights is associated with a respective partner of the plurality of partners. The processor then receives the plurality of customer requests associated with the plurality of customers and generate distribution data based on the received plurality of customer requests and the computed plurality of weights. The generated distribution data indicates that the plurality of customer requests is mapped to the plurality of partners. Finally, the processor processes the plurality of customer requests based on the generated distribution data.
In some example embodiments, to compute the plurality of weights for the at least one customer segment, the processor is further configured to determine target capital data associated with the plurality of partners for the at least one customer segment based on the acquired partner data. The processor computes total capital data associated with the plurality of partners for the at least one customer segment based on the determined target capital data and computes the plurality of weights associated with the plurality of partners for the at least one customer segment based on the determined target capital data, the computed total capital data, and the acquired first disbursed data.
In some example embodiments, to generate the distribution data, the processor is further configured to normalize the computed plurality of weights and store the normalized plurality of weights in an array in a specific order. The processor then executes a pseudo-random algorithm to generate a plurality of pseudo-random numbers for the plurality of customer requests and generates the distribution data based on the generated plurality of pseudo-random numbers and the array.
In some example embodiments, the processor is further configured to receive a timing signal and acquire second disbursed data associated with the plurality of partners for the at least one customer segment. The second disbursed data is acquired based on the received timing signal. The processor further recomputes the plurality of weights associated with the plurality of partners based on the acquired second disbursed data.
In some example embodiments, the processor is further configured to identify a partner status of each partner of the plurality of partners and recompute the plurality of weights associated with the plurality of partners based on the identified partner status.
In some example embodiments, the processor is further configured to receive partner configuration information of at least one partner of the plurality of partners and recompute at least one weight of the plurality of weights associated with the at least one partner based on the received partner configuration information.
In some example embodiments, the processor is further configured to detect an anomaly in the processing of the plurality of customer requests and output a notification based on the detected anomaly.
In some example embodiments, each weight of the computed plurality of weights indicates a number of customer requests to be mapped for the respective partner of the plurality of partners.
In some example embodiments, the first disbursed data associated with the plurality of partners indicates an amount of money that is disbursed by each partner of the plurality of partners.
In some example embodiments, the partner data associated with the plurality of partners further includes capital information of each partner of the plurality of partners. To process the plurality of customer requests, the processor is further configured to authorize the plurality of customer requests based on the generated distribution data and the capital information of each partner of the plurality of partners.
In another aspect of the present disclosure, a method is provided. A processor acquires partner data associated with a plurality of partners. The acquired partner data includes risk information associated with at least one customer segment of the plurality of customers. Further, the processor acquires first disbursed data associated with the plurality of partners for the at least one customer segment. A plurality of weights for the at least one customer segment is then computed based on the acquired partner data and the acquired first disbursed data. Each weight of the computed plurality of weights is associated with a respective partner of the plurality of partners. The processor receives the plurality of customer requests associated with the plurality of customers and generates distribution data based on the received plurality of customer requests and the computed plurality of weights. The generated distribution data indicates that the plurality of customer requests is mapped to the plurality of partners. Finally, the processor processes the plurality of customer requests based on the generated distribution data.
It is an objective of the disclosed system and method to efficiently manage the resource (e.g., capital) of the plurality of partners. To this end, the disclosed system and method aim to map the plurality of customer requests, associated with the at least one customer segment (e.g., a high-risk customer segment), to the plurality of partners. In order to map the plurality of customer requests to the plurality of partners, the disclosed system and method compute the plurality of weights for the at least one customer segment, where each weight of the plurality of weights indicates a number of customer requests to be mapped for a respective partner of the plurality of partners. Further, the disclosed system and method utilize the computed weights to process the plurality of customer requests, and thereby achieving the objective.
BRIEF DESCRIPTION OF THE DRAWINGS
The following detailed description of the embodiments of the present disclosure will be better understood when read in conjunction with the appended drawings. The present disclosure is illustrated by way of example, and not limited by the accompanying figures, in which like references indicate similar elements.
FIG. 1 illustrates a network environment for processing a plurality of customer requests associated with a plurality of customers, in accordance with an example embodiment of the present disclosure;
FIG. 2A illustrates a process pipeline for processing the plurality of customer requests, in accordance with an example embodiment of the present disclosure;
FIG. 2B illustrates a flowchart for acquiring partner data associated with a plurality of partners, in accordance with an example embodiment of the present disclosure;
FIG. 2C illustrates a flowchart for computing a plurality of weights associated with the plurality of partners, in accordance with an example embodiment of the present disclosure;
FIG. 2D illustrates a flowchart for generating distribution data, in accordance with an example embodiment of the present disclosure;
FIG. 3A illustrates a process pipeline for recomputing the plurality of weights associated with the plurality of partners, in accordance with an example embodiment of the present disclosure;
FIG. 3B illustrates a flowchart for recomputing the plurality of weights, in accordance with an example embodiment of the present disclosure;
FIG. 3C illustrates a flowchart for identifying partner statuses of the plurality of partners, in accordance with an example embodiment of the present disclosure;
FIG. 4 illustrates a flowchart for detecting one or more anomalies in the processing of the plurality of customer requests, in accordance with an example embodiment of the present disclosure;
FIG. 5 illustrates a flowchart for processing the plurality of customer requests in an E-commerce service platform, in accordance with an example embodiment of the present disclosure; and
FIG. 6 illustrates a block diagram of a computer system for processing the plurality of customer requests associated with the plurality of customers, in accordance with an example embodiment of the present disclosure.
Further areas of applicability of the present disclosure will become apparent from the detailed description provided hereinafter. It should be understood that the detailed description of exemplary embodiments is intended for illustration purposes only and is, therefore, not intended to necessarily limit the scope of the present disclosure.
DETAILED DESCRIPTION
The present disclosure is best understood with reference to the detailed figures and description set forth herein. Various embodiments are discussed below with reference to the figures. However, those skilled in the art will readily appreciate that the detailed descriptions given herein with respect to the figures are simply for explanatory purposes as the methods and systems may extend beyond the described embodiments. In one example, the teachings presented and the needs of a particular application may yield multiple alternate and suitable approaches to implement the functionality of any detail described herein. Therefore, any approach may extend beyond the particular implementation choices in the following embodiments that are described and shown.
References to “an embodiment”, “another embodiment”, “yet another embodiment”, “one example”, “another example”, “yet another example”, “for example”, “for instance”, and so on, indicate that the embodiment(s) or example(s) so described may include a particular feature, structure, characteristic, property, element, or limitation, but that not every embodiment or example necessarily includes that particular feature, structure, characteristic, property, element or limitation. Furthermore, repeated use of the phrase “in an embodiment” does not necessarily refer to the same embodiment.
TERMS DESCRIPTION (in addition to plain and dictionary meaning)
Loan servicing platform may be a server that provides loans to loan borrowers, and collects principal, interest, and/or escrow payments from the loan borrowers for the provided loans. Examples of servers may include, but are not limited to, a computer, a mini-computer, a mainframe computer, a cloud-based server, distributed server networks, a network of computer systems, or a combination thereof.
Partner may refer to a lender who wish to lend their money to provide loans. Examples of lender may include, but are not limited to, an individual, a financial institution, a public sector unit, or a combination thereof.
Partner data of a partner may include at least one of capital information or risk information. The capital information may indicate a capital (e.g., an amount of money) that the partner wishes to lend to a customer. The risk information may indicate a risk value (or a risk percentage) that the partner wishes to take for lending the capital.
Disbursed data of a partner may indicate an amount of money that is disbursed by the partner from a start time for a specific time. The specific time may be a week, a month, a year, or the like.
Customer may refer to a loan borrower. The customer may include, but are not limited to, an individual, an organization, a combination thereof.
A risk score of a customer may correspond to one or more of a value, a percentage, or a probability indicating whether the loan borrowed by the customer will be paid or not. A low-risk score may indicate that the loan borrowed by the customer will be paid in timely manner. A high-risk score may indicate that the loan borrowed by the customer will not be paid in timely manner.
Customer request of a customer may be a request for a loan application. The customer request may include at least one of loan amount information and/or customer personal information. The loan amount information may indicate a loan amount that the customer wishes to borrow. The customer personal information may include information indicating one or more of a name of the customer, a contact number of the customer, an address of the customer, an email address of the customer, nature of business of the customer, and/or the like.
FIG. 1 illustrates a network environment 100 for processing a plurality of customer requests associated with a plurality of customers 102, in accordance with an example embodiment of the present disclosure. As illustrated in FIG. 1, the network environment 100 may include a plurality of customer devices 104, a plurality of partner devices 108, a network 110, and a system 112. In various embodiments, the system 112 may be a loan servicing platform that provides loans to the plurality of customers 102, and collects principal, interest, and/or escrow payments from the plurality of customers 102 for the provided loans. As used herein, ‘customer’ may correspond to a loan borrower. For instance, each customer of the plurality of customers 102 may be an individual or an organization. The system 112 may be realized through various web-based technologies such as a Java web framework, a .NET framework, a PHP framework, or any other web-application framework. Examples of the system 112 may include, but are not limited to, a computer, a laptop, a mini-computer, a mainframe computer, a cloud-based server, distributed server networks, a network of computer systems, and/or the like. The system 112 may be associated with a financial technology company, a banking institution, or the like. The financial technology company or the banking institution may have a plurality of partners 106 who wish to lend their money to process the loans. For instance, each partner of the plurality of partners 106 may be an individual, a financial institution, a public sector unit, and/or the like.
In various embodiments, the system 112 may be communicatively coupled to the plurality of customer devices 104 and/or the plurality of partner devices 108 via the network 110. The network 110 may include a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a satellite network, the Internet, a fiber optic network, a coaxial cable network, an infrared (IR) network, a radio frequency (RF) network, and/or the like. Various entities in the network environment 100 may connect to the network 110 in accordance with various wired and wireless communication protocols, such as Transmission Control Protocol and Internet Protocol (TCP/IP), User Datagram Protocol (UDP), Long Term Evolution (LTE) communication protocols, New Radio (NR) communication protocols, and/or the like.
The plurality of customer devices 104 may include a first customer device 104a, a second customer device 104b, and so on up to an Nth customer device 104n. For instance, each customer device of the plurality of customer devices 104 may correspond to a smartphone, a laptop, a tablet, a Personal Computer (PC), and/or the like. The plurality of customer devices 104 may be associated with the plurality of customers 102. In an embodiment, each customer device of the plurality of customer devices 104 may be associated with a respective customer of the plurality of customers 102. For instance, the first customer device 104a may be associated with a first customer 102a of the plurality of customers 102 and the second customer device 104b may be associated with a second customer 102b of the plurality of customers 102, and so forth.
In various embodiments, each customer device of the plurality of customer devices 104 may be utilized by the respective customer of the plurality of customers 102 to raise a customer request. For instance, the customer request may be a request for a loan application. The customer request may include loan amount information and/or customer personal information. For instance, the loan amount information may indicate a loan amount that a customer wishes to borrow. The customer personal information may include information indicating one or more of a name of the customer, a contact number of the customer, an address of the customer, an email address of the customer, nature of business of the customer, and/or the like.
In various embodiments, customer requests of the plurality of customers 102 may be categorized into a plurality of customer segments. The categorization of each customer request of the customer requests may be based on features of the respective customer, such as one or more of, nature of business of the respective customer, mortgage provided by the respective customer, nature of repayment of a loan borrowed by the respective customer, or the like. In an embodiment, the plurality of customer segments may include a first customer segment, a second customer segment, and so on up to Nth customer segment. Each customer segment of the plurality of customer segments may be associated with a risk range. For instance, the first customer segment may be associated with a risk range of 0%-5% and the second customer segment may be associated with a risk range of 5%-10%. In an embodiment, a customer segment whose risk range is highest among the plurality of customer segments may be a high-risk customer segment. Alternatively, a customer segment whose risk range is lowest among the plurality of customer segments may be a low-risk customer segment.
The plurality of partner devices 108 may include a first partner device 108a, a second partner device 108b, and so on up to an Nth partner device 108n. For instance, each partner device of the plurality of partner devices 108 may correspond to a smartphone, a laptop, a tablet, a PC, and/or the like. The plurality of partner devices 108 may be associated with a plurality of partners 106. In an embodiment, each partner device of the plurality of partner devices 108 may be associated with a respective partner of the plurality of partners 106. For instance, the first partner device 108a may be associated with a first partner 106a of the plurality of partners 106 and the second partner device 108b may be associated with a second partner 106b of the plurality of partners 106, and so forth.
In various embodiments, each partner device of the plurality of partner devices 108 may be utilized by the respective partner of the plurality of partners 106 to generate partner data. In an embodiment, the partner data of each partner of the plurality of partners 106 may include at least one of capital information and/or risk information. For instance, the capital information may indicate a capital (for example, an amount of money) that a partner wishes to lend to a prospective borrower, i.e., a customer. For instance, the risk information may indicate a risk value (or a risk percentage) that the partner wishes to take for lending the capital.
When customer requests associated with the high-risk customer segment is received, conventional systems may map the received customer requests to a single partner, of the plurality of partners 106, whose risk information indicates the highest risk value. Due to this, capital of some partners is over-utilized and capital of some other partners is under-utilized. Consequently, manual efforts are required to efficiently manage capital of the plurality of partners 106. It is an objective of some embodiments of the present disclosure to efficiently utilize the capital of each partner of the plurality of partners 106, such that the manual efforts of managing the capital of the plurality of partners 106 are reduced. To this end, some embodiments aim to map the received customer requests to the plurality of partners 106, rather than mapping to the single partner. In order to map the customer requests, in some embodiments, the system 112 may be configured to compute a plurality of weights for the high-risk customer segment, where each weight of the plurality of weights indicates a number of customer requests to be mapped for a respective partner of the plurality of partners 106. The system 112 may be further configured to process the customer requests using the computed plurality of weights.
In an embodiment, the system 112 may include at least one processor 112a, a memory 112b, and a communication interface 112c. In an embodiment, the at least one processor 112a may be communicatively coupled to the memory 112b and/or the communication interface 112c. The at least one processor 112a may include one or more single or multi-core central processing units (CPUs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), and/or the like. The memory 112b may include non-volatile memory, volatile memory, read only memory (ROM), random access memory (RAM), flash memory, magnetic storage, and/or any other suitable memory. The communication interface 112c may be an I/O interface for communicating with one or more I/O devices and/or may be a network interface for communicating with one or more external devices (such as the plurality of customer devices 104 and/or the plurality of partner devices 108). For instance, the I/O devices may include a monitor, a mouse, a keyboard, a camera, a touchpad, a speaker, a microphone, a joystick, and/or the like.
In an embodiment, the memory 112b may be configured to store computer-executable instructions (e.g., software code(s)) for processing the customer requests associated with the plurality of customers 102. In an embodiment, upon execution of the computer-executable instructions, the at least one processor 112a may be configured as a weight computer112d and/or a customer request processor 112e. When the at least one processor 112a is configured as the weight computer 112d, the at least one processor 112a may be configured to receive the partner data associated with each partner of the plurality of partners 106. For instance, the partner data may be received from the plurality of partner devices 108. The at least one processor 112a may be further configured to compute, for each customer segment of the plurality of customer segments, the plurality of weights associated with the plurality of partners 106 based on the received partner data.
When the at least one processor 112a is configured as the customer request processor 112e, the at least one processor 112a may be configured to receive a plurality of customer requests associated with the plurality of customers 102. For instance, the plurality of customer requests may be received from the plurality of customer devices 104. The at least one processor 112a may be further configured to process, based on the computed plurality of weights, the received plurality of customer requests. For instance, the computation of the plurality of weights and the processing of the plurality of customer requests are explained in the detailed description of FIG. 2A-FIG. 2D.
FIG. 2A illustrates a process pipeline 200a for processing the plurality of customer requests, in accordance with an example embodiment of the present disclosure. FIG. 2A is explained in conjunction with FIG. 1. In an embodiment, the at least one processor 112a of the system 112 may execute the process pipeline 200a upon execution of the computer-executable instructions stored in the memory 112b. In another embodiment, the at least one processor 112a of the system 112 may include a specialized hardware (or a specialized circuitry) that is configured to execute the process pipeline 200a. For instance, the specialized hardware/the specialized circuitry may be realized by one or more of ASICs, FPGAs, and/or the like.
At block 202, the at least one processor 112a may be configured to acquire the partner data associated with the plurality of partners 106. For instance, the at least one processor 112a may acquire the partner data as explained in the detailed description of FIG. 2B.
FIG. 2B illustrates a flowchart 200b for acquiring the partner data associated with the plurality of partners 106, in accordance with an example embodiment of the present disclosure. FIG. 2B is explained in conjunction with FIG. 1 and FIG. 2A. For instance, the at least one processor 112a may execute a series of steps 202a-202d for acquiring the partner data associated with the plurality of partners 106. Hereinafter, ‘partner data associated with the plurality of partners’ and ‘plurality of pieces of partner data’ may be interchangeably used to mean the same.
At step 202a, the at least one processor 112a may be configured to receive, from the plurality of partner devices 108, a plurality of pieces of partner data. Each piece of partner data of the plurality of pieces of partner data is associated with the respective partner of the plurality of partners 106. In various embodiments, each piece of partner data of the plurality of pieces of partner data may include at least one of the capital information of the respective partner and/or the risk information of the respective partner. For instance, the capital information of the respective partner may indicate a capital that the respective partner wishes to lend. For instance, the risk information of the respective partner may indicate a risk value (or a risk score) that the respective partner wishes to take for lending the capital. In an embodiment, the risk information included in each piece of partner data of the plurality of pieces of partner data may be associated with one or more customer segments of the plurality of customer segments. In various embodiments, each customer segment of the plurality of customer segments may be associated the risk range. For instance, the risk information included in each piece of partner data of the plurality of pieces of partner data may be associated with a particular customer segment of the plurality of customer segments if the risk information indicates a risk that is within the risk range of the particular customer segment.
At step 202b, the at least one processor 112a may be further configured store the received plurality of pieces of partner data in a partner database. In one embodiment, the partner database may be embodied within the memory 112b. In another embodiment, the partner database may be provided as a separate entity in the system 112 to store the received plurality of pieces of partner data.
At step 202c, the at least one processor 112a may be configured to receive a first timing signal indicating a start trigger. For instance, the at least one processor 112a may receive the first timing signal from a clock, a timer, and/or a scheduler associated with the system 112. For instance, the start trigger may be a start time of a specific time period, a start time to start the computation of the plurality of weights and/or a start time to start the processing of the plurality of customer requests. For instance, the specific time period may be a week, a month, or the like.
At step 202d, the at least one processor 112a may be configured to acquire, from the partner database, the plurality of pieces of partner data. For instance, the at least one processor 112a may acquire the plurality of pieces of partner data in response to the reception of the first timing signal.
Referring now to FIG. 2A, at block 204, the at least one processor 112a may be configured to acquire disbursed data associated with the plurality of partners 106. For instance, the disbursed data associated with the plurality of partners 106 may be acquired from a database 206. In one embodiment, the database 206 may be embodied within the memory 112b. In another embodiment, the database 206 may be provided as a separate entity in the system 112. Hereinafter, ‘disbursed data associated with the plurality of partners’ and ‘plurality of pieces of disbursed data’ may be interchangeably used to mean the same. In various embodiments, the database 206 may be configured to store a plurality of pieces of disbursed data for each customer segment of the plurality of customer segments, where each piece of disbursed data of the plurality of pieces of disbursed data may be associated with the respective partner of the plurality of partners. For instance, each piece of disbursed data of the plurality of pieces of disbursed data for a particular customer segment of the plurality of customer segments may indicate an amount of money that is currently disbursed by the respective partner, for the particular customer segment, from the start time of the specific time period.
In one embodiment, at block 204, the at least one processor 112a may be configured to acquire, from the database 206, the plurality of pieces of disbursed data for one particular customer segment of the plurality of customer segments. For instance, the at least one processor 112a may be configured to acquire the plurality of pieces of disbursed data for the high-risk customer segment of the plurality of customer segments. In another embodiment, at block 204, the at least one processor 112a may be configured to acquire, from the database 206, the plurality of pieces of disbursed data for each customer segment of the plurality of customer segments.
At block 208, the at least one processor 112a may be configured to compute the plurality of weights associated with the plurality of partners 106, where each weight of the plurality of weights is associated with the respective partner of the plurality of partners 106. In one embodiment, the at least one processor 112a may compute the plurality of weights for one particular customer segment of the plurality of customer segments. In another embodiment, the at least one processor 112a may compute the plurality of weights for each customer segment of the plurality of customer segments. In various embodiments, the plurality of weights may be computed based on the acquired partner data and the acquired disbursed data. For instance, the at least one processor 112a may compute the plurality of weights associated with the plurality of partners 106 as explained in the detailed description of FIG. 2C.
FIG. 2C illustrates a flowchart 200c for computing the plurality of weights associated with the plurality of partners 106, in accordance with an example embodiment of the present disclosure. FIG. 2C is explained in conjunction with FIG. 1, FIG. 2A, and FIG. 2B. For instance, the at least one processor 112a may execute a series of steps 208a-208c for computing the plurality of weights associated with the plurality of partners 106.
At step 208a, the at least one processor 112a may be configured to determine target capital data associated with the plurality of partners 106 for each customer segment of the plurality of customer segments based on the acquired partner data. Hereinafter, ‘target capital data associated with the plurality of partners 106’ and ‘plurality of pieces of target capital data’ may be interchangeably used to mean the same. In an embodiment, the at least one processor 112a may execute one or more models to determine a plurality of pieces of target capital data for each customer segment of the plurality of customer segments, where each piece of target capital data of the plurality of pieces of target capital data is associated with the respective partner of the plurality of partners 106. For example, the one or more models may include Machine Learning (ML) models, Deep Learning (DL) models, and/or the like. As used herein, ‘model’ may be a pre-trained ML/DL model that is configured to output a specific output. In an embodiment, an output of the one or more models may include the plurality of pieces of target capital data. For instance, each piece of target capital data of the plurality of pieces of target capital data for a particular customer segment of the plurality of customer segments may indicate an amount of money that the respective partner would be lending from their capital for the particular customer segment for the specific time period. In an embodiment, an input of the one or more models may include the risk range associated with each customer segment of the plurality of segments, the risk information included in the acquired partner data, and/or the capital information included in the acquired partner data. In various embodiments, the one or more models may be pre-trained using a training dataset that includes a plurality of pieces of historical target capital data of the plurality of partners 106. For instance, each piece of historical target capital data of the plurality of pieces of historical target capital data may indicate an amount of money that a partner of the plurality of partners 106 has lent in past for the particular customer segment for the specific time period. In an example embodiment, at step 208a, the at least one processor 112a may be further configured to store the determined plurality of pieces of target capital data in the database 206.
At step 208b, the at least one processor 112a may be configured to compute total capital data associated with the plurality of partners 106 for each customer segment of the plurality of customer segments based on the determined plurality of pieces of target capital data. For instance, the at least one processor 112a may compute the total capital data associated with the plurality of partners 106 for a particular customer segment of the plurality of customer segments by summing each piece of target capital data of the plurality of pieces of target capital data of the particular customer segment.
At step 208c, the at least one processor 112a may be configured to compute the plurality of weights for each customer segment of the plurality of customer segments based on the determined target capital data, the computed total capital data, and the acquired disbursed data. For instance, the at least one processor 112a may compute the plurality of weights for a particular customer segment of the plurality of customer segments based on the plurality of pieces of target capital data determined for the particular customer segment, the total capital data computed for the particular customer segment, the disbursed data acquired for the particular customer segment. For instance, each weight of the computed plurality of weights may indicate a number of customer requests to be mapped for the respective partner of the plurality of partners. For example, a weight of the plurality of weights that is associated with a particular partner of the plurality of partners 106 may be computed as shown in Equation 1:
Partner^' s weight = ((Partner^' s target captial data-Partner^' s disbursed data) )/(total capital data) ×100 (Equation 1).
Additionally, in some embodiments, the at least one processor 112a may be further configured to store the computed plurality of weights for each customer segment of the plurality of customer segments in the database 206.
Referring back to FIG. 2A, at block 210, the at least one processor 112a may be configured to receive the plurality of customer requests associated with the plurality of customers 102. For instance, the plurality of customer requests associated with the plurality of customers 102 may be received from the plurality of customer devices 104. In an embodiment, each customer request of the plurality of customer requests may include at least one of the loan amount information or the customer personal information.
At block 212, the at least one processor 112a may be configured to generate, based on the computed plurality of weights and the received plurality of customer requests, distribution data indicating that the plurality of customer requests is mapped to the plurality of partners 106. For instance, the at least one processor 112a may generate the distribution data as explained in the detailed description of FIG. 2D.
FIG. 2D illustrates a flowchart 200d for generating the distribution data, in accordance with an example embodiment of the present disclosure. FIG. 2D is explained in conjunction with FIG. 1 and FIG. 2A-FIG.2C. For instance, the at least one processor 112a may execute a series of steps 212a-212f for generating the distribution data.
At step 212a, the at least one processor 112a may be configured to categorize the plurality of customer requests into the plurality of customer segments. In an embodiment, the at least one processor 112a may be configured to execute one or more classifiers to categorize the plurality of customer requests. For instance, the one or more classifiers may include, but are not limited to, a convolutional neural network (CNN), a recurrent neural network (RNN), a radial basis functional neural network, a deep neural network model, a long short-term memory (LSTM) model, or the like. In an embodiment, the one or more classifiers may be pre-trained to determine a risk score for each customer request of the plurality of customer requests based on a customer profile associated the respective customer of the plurality of customers 102. For instance, the customer profile associated with the respective customer may include, but are not limited to, nature of business of the respective customer, mortgage provided by the respective customer, nature of repayment of the loan borrowed by the respective customer, a past risk score of the respective customer, and/or the like. In various embodiments, the one or more classifiers may be pre-trained using a training dataset that includes a plurality of pieces of historical risk score data of past customers. For instance, each piece of historical risk score data of the plurality of pieces of historical risk score data may indicate a past risk score of a past customer of the past customers that is determined for a customer profile of the past customer. Further, the one or more classifiers may be pre-trained to categorize the plurality of customer requests based on the risk score of each customer request of the plurality of customer requests and the risk range associated with each customer segment of the plurality of customer segments. For instance, a particular customer request of the plurality of customer requests may be added to a particular customer segment of the plurality of customer segments, if the risk score of the particular customer request matches the risk range of the particular customer segment.
At step 212b, the at least one processor 112a may be configured to acquire, from the database 206, the plurality of weights associated with the plurality of partners for each customer segment of the plurality of customer segments. At step 212c, the at least one processor 112a may be configured to normalize the acquired plurality of weights to fall within a specific range. In an example embodiment, the at least one processor 112a may divide each weight of the plurality of weights by a specific number to normalize the plurality of weights. For instance, the specific range may be a range from zero to one. For instance, the specific number may be determined based on the specific range.
At step 212d, the at least one processor 112a may be configured to generate an array to store the normalized plurality of weights. For instance, the generated array may be a cumulative array. In one embodiment, the array may be generated for each customer segment of the plurality of customer segments. In another embodiment, a single array may be generated for the plurality of customer segments. In various embodiments, the normalized plurality of weights may be stored in the generated array in a specific order (e.g., an ascending order).
At step 212e, the at least one processor 112a may be configured to execute a pseudo-random algorithm to generate a plurality of pseudo-random numbers for the plurality of customer requests. For instance, the pseudo-random algorithm may be a Well Equidistributed Long-period Linear (WELL) algorithm. Each pseudo-random number of the generated plurality of pseudo-random numbers may be associated with a respective customer request of the plurality of customer requests. In an embodiment, each pseudo-random number of the generated plurality of pseudo-random numbers may be within the specific range that is used for the normalization of the plurality of weights.
At step 212f, the at least one processor 112a may be configured to generate the distribution data based on the generated plurality of pseudo-random numbers and the generated array. Hereinafter, ‘distribution data’ and ‘plurality of pieces of distribution information’ may be interchangeably used to mean the same. For instance, the at least one processor 112a may be configured to generate a plurality of pieces of distribution information for the plurality of customer requests based on the generated plurality of pseudo-random numbers and the generated array. Each piece of distribution information of the plurality of pieces of distribution information may be associated with the respective customer request of the plurality of customer requests. In an embodiment, to generate a particular piece of distribution information of the plurality of pieces of distribution information for a particular customer request of the plurality of customer requests, the at least one processor 112a may identify, in the generated array, a normalized weight of the normalized plurality of weights that matches the pseudo-random number of the particular customer request. Further, the at least one processor 112a may retrieve, using the generate array, an index of the identified normalized weight. Furthermore, the at least one processor 112a may generate the particular piece of distribution information indicating that particular customer request is mapped to a partner of the plurality of partners 106 corresponding to the retrieved index. In an embodiment, the generated plurality of pieces of distribution information may indicate that the plurality of customer requests is mapped to the plurality of partners 106.
Referring back to FIG. 2A, at block 214, the at least one processor 112a may be configured to process the plurality of customer requests based on the generated plurality of pieces of distribution information (i.e., the generated distribution data). In an example embodiment, the processing of the plurality of customer requests may include authorizing of the plurality of customer requests. For instance, the at least one processor 112a may authorize the plurality of customer requests based on the generated plurality of pieces of distribution information and the capital information of each partner of the plurality of partners 106. For example, to authorize a particular customer request of the plurality of customer requests, the at least one processor 112a may obtain, from the plurality of pieces of distribution information, the particular piece of distribution information associated with the particular customer request. Further, the at least one processor 112a may identify the partner mapped to the particular customer request using the obtained particular piece of distribution information. Furthermore, the at least one processor 112a may sanction the loan amount indicated in the loan amount information of the particular customer request using the capital indicated in the capital information of the identified partner.
In this way, the at least one processor 112a may process the plurality of customer requests by utilizing the plurality of weights computed for the at least one customer segment (i.e., the high-risk customer segment), where each weight of the plurality of weights indicates the number of customer requests among the plurality of customer requests to be mapped for the respective partner of the plurality of partners 106. Accordingly, the at least one processor 112a is enabled to map the plurality of customer requests to the plurality of partners 106. Thereby, the at least one processor 112a enables efficient utilization of the capital of each partner, such that the manual efforts on managing the capital of the plurality of partners 106 are reduced.
Additionally, in some embodiments, the at least one processor 112a may be further configured to update the disbursed data associated with the plurality of partners 106 at step 216. In an embodiment, the least one processor 112a may update the disbursed data associated with the plurality of partners 106 based on the processing of the plurality of customer requests. For instance, when the loan amount is sanctioned for the particular customer of the plurality of customers 102, the least one processor 112a may increase the amount of money indicated in the piece of disbursed data of the mapped partner by the sanctioned loan amount. Furthermore, the at least one processor 112a may be configured to store the updated disbursed data associated with the plurality of partners 106 in the database 206. Hereinafter, the disbursed data acquired at the block 204 may be referred to as ‘first disbursed data’. Hereinafter, the updated disbursed data may be referred to as ‘second disbursed data’.
Some embodiments are based on a recognition that the update of the first disbursed data associated with the plurality of partners 106 may not affect the computed plurality of weights for a particular period of time from the start time indicated in the start trigger. However, after the particular period of time, the computed plurality of weights may be affected, since the computation of the plurality of weights is based on the first disbursed data. For instance, the particular period of time may be two hours, five hours, twenty-four hours, or the like. To this end, it is an objective of some embodiments of the present disclosure to recompute the plurality of weights associated with the plurality of partners 106 based on the second disbursed data (i.e., the updated disbursed data). For instance, the plurality of weights associated with the plurality of partners 106 may be recomputed as explained in the detailed description of FIG. 3A-FIG.3C.
FIG. 3A illustrates a process pipeline 300a for recomputing the plurality of weights associated with the plurality of partners 106, in accordance with an example embodiment of the present disclosure. FIG. 3A is explained in conjunction with FIG. 1 and FIG. 2A-FIG. 2D. For instance, the at least one processor 112a of the system 112 may execute the process pipeline 300a for recomputing the plurality of weights associated with the plurality of partners 106.
At block 302, the at least one processor 112a may be configured to receive a second timing signal. For instance, the at least one processor 112a may receive the second timing signal from one or more of the clock, the timer, and/or the scheduler associated with the system 112.
At block 304, the at least one processor 112a may be configured to recompute the plurality of weights associated with the plurality of partners 106 based on the received second timing signal. For instance, the at least one processor 112a may recompute the plurality of weights associated with the plurality of partners 106 as explained in the detailed description of FIG. 3B.
FIG. 3B illustrates a flowchart 300b for recomputing the plurality of weights, in accordance with an example embodiment of the present disclosure. FIG. 3B is explained in conjunction with FIG. 1, FIG. 2A-FIG. 2D, and FIG. 3A. For instance, the at least one processor 112a may execute a series of steps 304a-304d for recomputing the plurality of weights based on the received second timing signal.
At step 304a, the at least one processor 112a may be configured to determine, based on the received second timing signal, whether the particular period of time is lapsed from the start time indicated in the start trigger. In a case where it is determined that the particular period of time is not lapsed from the start time, the at least one processor 112a may wait until the particular period of time is lapsed.
In a case where it is determined that the particular period of time is lapsed from the start time, the at least one processor 112a may proceed with step 304b. At step 304b, the at least one processor 112a may be configured to acquire the second disbursed data associated with the plurality of partners 106. For instance, the at least one processor 112a may acquire the second disbursed data (i.e., the updated disbursed data) from the database 206.
At step 304c, the at least one processor 112a may be configured to acquire the partner data associated with the plurality of partners 106. For instance, the partner data associated with the plurality of partners 106 may be acquired from the partner database. At step 304d, the at least one processor 112a may be configured to recompute the plurality of weights associated with the plurality of partners 106 based on the acquired partner data and the acquired second disbursed data. For instance, the at least one processor 112a may recompute the plurality of weights associated with the plurality of partners 106 using the acquired partner data and the acquired second disbursed data as explained in the detailed description of FIG. 2A and FIG. 2C.
In this way, the at least one processor 112a may recompute the plurality of weights associated with the plurality of partners 106 when the particular period of time is lapsed from the start time. Some embodiments are based on a realization that the plurality of weights may also be affected by other parameters. For instance, the parameters that affect the plurality of weights may include partner statuses of the plurality of partners 106 and/or partner configurations of the plurality of partners 106. To this end, it is objective of some embodiments of the present disclosure to consider the partner statuses of the plurality of partners 106 and/or partner configurations of the plurality of partners 106 while computing the plurality of weights.
Referring back to FIG. 3A, at block 306, the at least one processor 112a may be configured to identify the partner statues of the plurality of partners 106. For instance, the at least one processor 112a may identify the partner statues of the plurality of partners 106 as explained in the detailed description of FIG. 3C.
FIG. 3C illustrates a flowchart 300c for identifying the partner statuses of the plurality of partners 106, in accordance with an example embodiment of the present disclosure. FIG. 3C is explained in conjunction with FIG. 1, FIG. 2A-FIG. 2D, and FIG. 3A. For instance, the at least one processor 112a may execute a series of steps 306a-306h for identifying the partner statuses of the plurality of partners 106.
At step 306a, the at least one processor 112a may be configured to acquire, from the database 206, a piece of disbursed data of the plurality of pieces of the disbursed data. For instance, the plurality of pieces of the disbursed data may correspond to one of the first disbursed data associated with the plurality of partners 106 or the second disbursed data associated with the plurality of partners 106. For instance, the acquired piece of disbursed data may be associated with the respective partner of the plurality of partners 106.
At step 306b, the at least one processor 112a may be configured to acquire, from the partner database, the capital information of the respective partner. For instance, the acquired capital information may indicate the capital that the respective partner wishes to lend.
At step 306c, the at least one processor 112a may be configured to compute remaining capital data of the respective partner based on the acquired piece of disbursed data and the acquired capital information. For instance, the at least one processor 112a may compute a difference, between the acquired piece of disbursed data and the acquired capital information, as the remaining capital data of the respective partner.
At step 306d, the at least one processor 112a may be configured to determine whether the remaining capital data of the respective partner is within a capital range. For instance, the capital range may be defined by a lower limit and a higher limit. For instance, the lower limit may be a first specific value (e.g., 2% of the capital indicated by the acquired capital information). For instance, the higher limit may be a second specific value (e.g., 10% of the capital indicated by the acquired capital information). In a case where it is determined that the remaining capital data of the respective partner is within the capital range, the at least one processor 112a may proceed with step 306e.
At step 306e, the at least one processor 112a may be configured identify a partner status of the respective partner as a soft-active partner. In a case whether it is determined that the remaining capital data of the respective partner is not within the capital range, the at least one processor 112a may proceed with step 306f.
At step 306f, the at least one processor 112a may be configured to determine whether the remaining capital data of the respective partner is less than the lower limit of the capital range. In a case where it is determined that the remaining capital data of the respective partner is less than the lower limit of the capital range, the at least one processor 112a may proceed with step 306g.
At step 306g, the at least one processor 112a may be configured to identify the partner status of the respective partner as an inactive partner. In a case where it is determined that the remaining capital data of the respective partner is not less than the lower limit of the capital range, the at least one processor 112a may proceed with step 306h. At step 306h, the at least one processor 112a may identify the partner status of the respective partner as an active partner. In this way, the at least one processor 112a may iteratively execute the flowchart 300c for each partner of the plurality of partners 106 to identify the partner status of each partner of the plurality of partners 106.
Referring back to FIG. 3A, at step 304, the at least one processor 112a may be configured to recompute the plurality of weights associated with the plurality of partners 106 based on the identified partner statues of the plurality of partners 106. In an example embodiment, when the partner status of a particular partner of the plurality of partners 106 is identified as the soft-active partner, the at least one processor 112a may compute a weight of the plurality of weights associated with the particular partner based on the generated array. For instance, the weight associated with the particular partner is computed as shown in Equation 2:
Partner^' s weight= -1×index of the array corresponding to partner (Equation 2).
For instance, when the partner status of the particular partner is identified as the active partner, the at least one processor 112a may compute the weight associated with the particular partner as explained in the detailed description of FIG. 2A and FIG. 2C. For instance, when the partner status of the particular partner is identified as the inactive partner, the at least one processor 112a may compute the weight associated with the particular partner as ‘0’.
At step 308, the at least one processor 112a may be configured to receive partner configuration information of at least one partner of the plurality of partners 106. For instance, the partner configuration information of the at least one partner may be received from at least one partner device of the plurality of partner devices 108. In an embodiment, the received partner configuration information may indicate that the at least one partner is not willing to lend the capital.
At step 304, the at least one processor 112a may be configured to recompute at least one weight, of the plurality of weights, associated with the at least one partner based on the received partner configuration information. For instance, upon the reception of the partner configuration information of the at least one partner, the at least one processor 112a may recompute the at least one weight associated with the at least one partner as ‘0’.
In some example embodiments, the recomputed plurality of weights may be further utilized by the at least one processor 112a to process the plurality of customer requests associated with the plurality of customers 102. For instance, the at least one processor 112a may regenerate, using the recompute plurality of weights, the distribution data as explained in the detailed description of FIG. 2D. Further, the at least one processor 112a may process the plurality of customer requests associated with the plurality of customers 102 by using the regenerated distribution data as explained in the detailed description of FIG. 2A.
In an example embodiment, when the plurality of weights is recomputed based on the partner statutes of the plurality of partners, the at least one processor 112a may be further configured to prioritize the recomputed plurality of weights while regenerating the distribution data. For instance, the at least one processor 112a may categorize the recomputed plurality of weights into one or more of a set of positive weights, a set of negative weights, and a set of zero weights. The set of positive weights may include weights associated with active partners of the plurality of partners 106. The set of negative weights may include weights associated with soft-active partners of the plurality of partners 106. The set of zero weights may include weights associated with inactive partners of the plurality of partners 106. For instance, while regenerating the distribution data, the at least one processor 112a may prioritize the set of positive weights over the set of negative weights and the set of zero weights, and further may prioritize the set of negative weights over the set of zero weights.
In this way, the at least one processor 112a may be configured to recompute the plurality of weights and utilize the recomputed plurality of weights to process the plurality of customer requests associated with the plurality of customers 102. Since the plurality of weights are recomputed using the partner configuration information and/or using the partner statuses that are identified based on the remaining capital data of each partner of the plurality of partners 106, the at least one processor 112a may be enabled to process the plurality of customer requests with an improved Turn Around Time (TAT) that is less than TAT provided by convention systems. Therefore, the at least one processor 112a improves customer experience while servicing the plurality of customer requests.
In some example embodiments, the at least one processor 112a may be further configured as an anomaly detector for detecting one or more anomalies in the processing of the plurality of customer requests. In an embodiment, upon the execution of the computer-executable instructions stored in the memory 112b of the system 112, the at least one processor 112a may be configured as the anomaly detector. For instance, the detection of the one or more anomalies in the processing of the plurality of customer requests is as explained in the detailed description of FIG. 4.
FIG. 4 illustrates a flowchart 400 for detecting the one or more anomalies in the processing of the plurality of customer requests, in accordance with an example embodiment of the present disclosure. FIG. 4 is explained in conjunction with FIG. 1, FIG. 2A-FIG. 2D, and FIG. 3A-FIG. 3C. For instance, the at least one processor 112a may execute a series of steps 402-412 for detecting the one or more anomalies in the processing of the plurality of customer requests.
At step 402, the at least one processor 112a may be configured to acquire, from the database 206, a piece of disbursed data of the plurality of pieces of disbursed data, where the acquired piece of disbursed data is associated with a particular partner of the plurality of partners 106. For instance, the at least one processor 112a may acquire the piece of disbursed data associated with the particular partner at regular intervals (e.g., for every one hour, two hours, or the like). For instance, the plurality of pieces of the disbursed data may correspond to one of the first disbursed data associated with the plurality of partners 106 or the second disbursed data associated with the plurality of partners 106.
At step 404, the at least one processor 112a may be configured to acquire, from the database 206, a piece of target capital data of the plurality of pieces of target data. For instance, the acquired piece of target capital data may be associated with the particular partner.
At step 406, the at least one processor 112a may be configured to compute available capital data of the particular partner based on the acquired piece of target capital data and the acquired piece of disbursed data. For instance, the at least one processor 112a may compute a difference, between the acquired piece of target capital data and the acquired piece of disbursed data, as the available capital data of the particular partner.
At step 408, the at least one processor 112a may be configured to determine whether the computed available capital data is greater than a threshold available capital data. For instance, the threshold available capital data may be determined based on a current interval of the regular intervals and the acquired piece of target capital data. In a case where it is determined that the computed available capital data is not greater than the threshold available capital data, the at least one processor 112a may proceed with step 402. At step 402, the at least one processor 112a may be configured to wait until a next interval of the regular intervals and again acquire the piece of disbursed data. For instance, the next interval is subsequent to the current interval.
In a case where it is determined that the computed available capital data is greater than the threshold available capital data, the at least one processor 112a may proceed with step 410. At step 410, the at least one processor 112a may be configured to detect that there is an anomaly associated with the particular partner. For instance, the detected anomaly may indicate that the available capital data of the particular partner is greater than the threshold available capital data for the current interval.
At step 412, the at least one processor 112a may be configured to output a notification based on the detected anomaly. For instance, the notification may include information about the detected anomaly. In an example embodiment, at step 412, the at least one processor 112a may be further configured to control one or more output devices of the system 112 to output the notification. Examples of the one or more output devices may include, but are not limited to, a monitor, a display screen, a speaker, or a combination of thereof.
In this way, the at least one processor 112a may iteratively execute the flowchart 400 for each partner of the plurality of partners 106 and for each customer segment of the plurality of customer segments to identify whether the capital of each partner of the plurality of partner 106 is correctly disbursed for each customer segment of the plurality of customer segments. Accordingly, the at least one processor 112a may reduce manual efforts on monitoring the disbursed data associated with the plurality of partners 106.
The detection of the one or more anomalies by the at least one processor 112a may not be limited to the flowchart 400. In some other example embodiments, the at least one processor 112a may be configured to monitor the plurality of customer requests to identify at least one customer request of the plurality of customer requests that is not mapped to a partner of the plurality of partners 106. Further, the at least one processor 112a may be configured to detect that there is an anomaly associated with the at least one customer request and output a notification based on the detected anomaly. Accordingly, in these embodiments, the at least one processor 112a may reduce manual efforts on monitoring the plurality of customer requests.
For the purpose of explanation, in FIG. 1, FIG. 2A-FIG. 2D, FIG. 3A-FIG. 3C, and FIG. 4, the system 112 is consider as the loan servicing platform. However, the system 112 may not to be limited to the loan servicing platform. In some example embodiments, the system 112 may be configured as an E-commerce (electronic commerce) service platform. In these embodiments, the plurality of partners 106 may correspond to a plurality of suppliers and the plurality of pieces of partner data may correspond to a plurality of pieces of supplier data. In these embodiments, an objective of the system 112 is to efficiently manage resource (e.g., goods) of the plurality of suppliers. To this end, the system 112 may be configured to compute a plurality of weights for the plurality of suppliers and utilize the computed weights to process the plurality of customer requests. For instance, a process executed by the system 112 (e.g., the E-commerce service platform) will be explained with reference to FIG. 5.
FIG. 5 illustrates a flowchart 500 for processing the plurality of customer requests in the E-commerce service platform, in accordance with an example embodiment of the present disclosure. FIG. 5 is explained in conjunction with FIG. 1, FIG. 2A-FIG. 2D, FIG. 3A-FIG. 3C, and FIG. 4. For instance, the at least one processor 112a of the system 112 may execute a series of steps 502-512 for processing the plurality of customer requests in the E-commerce service platform.
At step 502, the at least one processor 112a may be configured to acquire the plurality of pieces of supplier data of the plurality of suppliers. For instance, the plurality of pieces of supplier data may be acquired from the plurality of suppliers as explained in the detailed description of FIG. 2B. In an embodiment, each piece of supplier data of the plurality of pieces of supplier data may include goods information of a respective supplier of the plurality of suppliers and/or risk information of the respective supplier. The goods information of the respective supplier may indicate a number of goods that the respective supplier wishes to supply. The risk information of the respective supplier may indicate a risk value that the respective supplier wishes to take for supplying the number of goods. Examples of the goods may include computers, laptops, mobile phones, books, bags, vehicles, or the like.
At step 504, the at least one processor 112a may be configured to acquire the plurality of pieces of disbursed data of the plurality of suppliers. For instance, the plurality of pieces of disbursed data may be acquired from the database 206 associated with the system 112 as explained in the detailed description of FIG. 2A. In an embodiment, each piece of disbursed data of the plurality of pieces of disbursed data may indicate a number of goods that are currently supplied by the respective supplier.
At step 506, the at least one processor 112a may be configured to compute the plurality of weights for the plurality of suppliers. For instance, the plurality of weights may be computed based on the acquired plurality of pieces of supplier data and the acquired plurality of pieces of disbursed data as explained in the detailed description of FIG. 2C. In an embodiment, each weight of the plurality of weights may indicate a number of customer requests to be mapped for the respective supplier of the plurality of suppliers.
At step 508, the at least one processor 112a may be configured to receive the plurality of customer requests associated with the plurality of customer 102. For instance, the plurality of customer requests may be received from the plurality of customer 102 as explained in the detailed description of FIG. 2A. In an embodiment, each customer of the plurality of customer 102 may correspond to a purchaser who wishes to purchase the goods from the plurality of suppliers. Further, the plurality of customer requests may correspond to requests for purchasing the goods from the suppliers.
At step 510, the at least one processor 112a may be configured to generate the distribution data based on the computed plurality of weights and the received plurality of customer requests. For instance, the distribution data may be generated as explained in the detailed description of FIG. 2D. In an embodiment, the generated distribution data may indicate the plurality of customer requests is mapped to the plurality of suppliers.
At step 512, the at least one processor 112a may be configured to process the plurality of customer requests based on the generated distribution data. For instance, the plurality of customer requests may be processed as explained in the detailed description of FIG. 2A. In an embodiment, the at least one processor 112a may be configured to authorize, using the generated distribution data, supply of the goods from the plurality of suppliers to the plurality of customers 102.
In this way, the at least one processor 112a may be enabled to efficiently manage the resource of the plurality of suppliers by computing the plurality of weights for the plurality of suppliers and utilizing the computed plurality of weights to process the plurality of customer requests.
FIG. 6 illustrates a block diagram of a computer system 600 for processing the plurality of customer requests associated with the plurality of customers 102, in accordance with an example embodiment of the present disclosure. FIG. 6 is explained in conjunction with FIG. 1, FIG. 2A-FIG. 2D, FIG. 3A-FIG. 3C, FIG. 4, and FIG. 5. An embodiment of the present disclosure, or portions thereof, may be implemented as computer-readable code on the computer system 600. In one example, the system 112 of FIG. 1 may be implemented in the computer system 600 using hardware, software, firmware, a non-transitory computer-readable medium having instructions stored thereon, or a combination thereof, and may be implemented in one or more computer systems or other processing systems. Hardware, software, or any combination thereof may embody modules and components used to implement the process described in FIG. 2A-FIG. 2D, the process described in FIG. 3A-FIG. 3C, the process described in FIG. 4, and/or the process described in FIG. 5.
The computer system 600 may include a processor 602 that may be a special-purpose or a general-purpose processing device. The processor 602 may be a single processor or multiple processors. The processor 602 may have one or more processor cores. Further, the processor 602 may be coupled to a communication infrastructure 604, such as a bus, a bridge, a message queue, a multi-core message-passing scheme, or the like. The computer system 600 may further include a main memory 606 and a secondary memory 608. Examples of the main memory 606 may include RAM, ROM, and the like. The secondary memory 608 may include a hard disk drive or a removable storage drive (not shown), such as a floppy disk drive, a magnetic tape drive, a compact disc, an optical disk drive, a flash memory, or the like. Further, the removable storage drive may read from and/or write to a removable storage device in a manner known in the art. In an embodiment, the removable storage unit may be a non-transitory computer-readable recording medium.
The computer system 600 may further include an input/output (I/O) port 610 and a communication interface 612. The I/O port 610 may include various input and output devices that are configured to communicate with the processor 602. Examples of the input devices may include a keyboard, a mouse, a joystick, a touchscreen, a microphone, and the like. Examples of the output devices may include a display screen, a speaker, headphones, and the like. The communication interface 612 may be configured to allow data to be transferred between the computer system 600 and various devices that are communicatively coupled to the computer system 600. Examples of the communication interface 612 may include a modem, a network interface, i.e., an Ethernet card, a communication port, and the like. Data transferred via the communication interface 612 may be signals, such as electronic, electromagnetic, optical, or other signals as will be apparent to a person skilled in the art. The signals may travel via a communications channel, such as the network 110, which may be configured to transmit the signals to the various devices that are communicatively coupled to the computer system 600. Examples of the communication channel may include wired, wireless, and/or optical media such as cable, fiber optics, a phone line, a cellular phone link, a radio frequency link, and the like. The main memory 606 and the secondary memory 608 may refer to non-transitory computer-readable mediums that may provide data that enables the computer system 600 to implement the process described in FIG. 2A-FIG. 2D, the process described in FIG. 3A-FIG. 3C, the process described in FIG. 4, and/or the process described in FIG. 5.
A person of ordinary skill in the art will appreciate that embodiments and exemplary scenarios of the disclosed subject matter may be practiced with various computer system configurations, including multi-core multiprocessor systems, minicomputers, mainframe computers, computers linked or clustered with distributed functions, as well as pervasive or miniature computers that may be embedded into virtually any device. Further, the operations may be described as a sequential process, however, some of the operations may in fact be performed in parallel, concurrently, and/or in a distributed environment, and with program code stored locally or remotely for access by single or multiprocessor machines. In addition, in some embodiments, the order of operations may be rearranged without departing from the spirit of the disclosed subject matter.
Techniques consistent with the disclosure provide, among other features, systems and methods for processing the customer requests in the loan servicing platform. While various exemplary embodiments of the disclosed systems and methods have been described above, it should be understood that they have been presented for purposes of example only, and not limitations. It is not exhaustive and does not limit the disclosure to the precise form disclosed. Modifications and variations are possible in light of the above teachings or may be acquired from practicing of the disclosure, without departing from the breadth or scope.
While various embodiments of the disclosure have been illustrated and described, it will be clear that the disclosure is not limited to these embodiments only. Numerous modifications, changes, variations, substitutions, and equivalents will be apparent to those skilled in the art, without departing from the spirit and scope of the disclosure, as described in the claims. , Claims:We Claim:
1. A system (112), comprising:
a memory (112b) configured to store computer-executable instructions; and
at least one processor (112a) communicatively coupled to the memory (112b), wherein the at least one processor (112a) is configured to execute the computer-executable instructions to:
acquire partner data associated with a plurality of partners (106), wherein the acquired partner data includes risk information associated with at least one customer segment of a plurality of customers (102);
acquire first disbursed data associated with the plurality of partners (106) for the at least one customer segment;
compute a plurality of weights for the at least one customer segment based on the acquired partner data and the acquired first disbursed data, wherein each weight of the computed plurality of weights is associated with a respective partner of the plurality of partners (106);
receive a plurality of customer requests associated with the plurality of customers (102);
generate distribution data based on the received plurality of customer requests and the computed plurality of weights, wherein the generated distribution data indicates that the plurality of customer requests is mapped to the plurality of partners (106); and
process the plurality of customer requests based on the generated distribution data.
2. The system (112) as claimed in claim 1, wherein to compute the plurality of weights for the at least one customer segment, the at least one processor (112a) is further configured to:
determine target capital data associated with the plurality of partners (106) for the at least one customer segment based on the acquired partner data;
compute total capital data associated with the plurality of partners (106) for the at least one customer segment based on the determined target capital data; and
compute the plurality of weights associated with the plurality of partners (106) for the at least one customer segment based on the determined target capital data, the computed total capital data, and the acquired first disbursed data.
3. The system (112) as claimed in claim 1, wherein to generate the distribution data, the at least one processor (112a) is further configured to:
normalize the computed plurality of weights;
store the normalized plurality of weights in an array in a specific order;
execute a pseudo-random algorithm to generate a plurality of pseudo-random numbers for the plurality of customer requests; and
generate the distribution data based on the generated plurality of pseudo-random numbers and the array.
4. The system (112) as claimed in claim 1, wherein the at least one processor (112a) is further configured to:
receive a timing signal;
acquire second disbursed data associated with the plurality of partners (106) for the at least one customer segment, wherein the second disbursed data is acquired based on the received timing signal; and
recompute the plurality of weights associated with the plurality of partners (106) based on the acquired second disbursed data.
5. The system (112) as claimed in claim 1, wherein the at least one processor (112a) is further configured to:
identify a partner status of each partner of the plurality of partners (106); and
recompute the plurality of weights associated with the plurality of partners (106) based on the identified partner status.
6. The system (112) as claimed in claim 1, wherein the at least one processor (112a) is further configured to:
receive partner configuration information of at least one partner of the plurality of partners (106); and
recompute at least one weight of the plurality of weights associated with the at least one partner based on the received partner configuration information.
7. The system (112) as claimed in claim 1, wherein the at least one processor (112a) is further configured to:
detect an anomaly in the processing of the plurality of customer requests; and
output a notification based on the detected anomaly.
8. The system (112) as claimed in claim 1, wherein each weight of the computed plurality of weights indicates a number of customer requests to be mapped for the respective partner of the plurality of partners (106).
9. The system (112) as claimed in claim 1, wherein the first disbursed data associated with the plurality of partners (106) indicates an amount of money that is disbursed by each partner of the plurality of partners (106).
10. The system (112) as claimed in claim 1, wherein
the partner data associated with the plurality of partners (106) further includes capital information of each partner of the plurality of partners (106), and
to process the plurality of customer requests, the at least one processor (112a) is further configured to authorize the plurality of customer requests based on the generated distribution data and the capital information of each partner of the plurality of partners (106).
11. A method, comprising:
acquiring, by at least one processor (112a), partner data associated with a plurality of partners (106), wherein the acquired partner data includes risk information associated with at least one customer segment of the plurality of customers (102);
acquiring, by the at least one processor (112a), first disbursed data associated with the plurality of partners (106) for the at least one customer segment;
computing, by the at least one processor (112a), a plurality of weights for the at least one customer segment based on the acquired partner data and the acquired first disbursed data, wherein each weight of the computed plurality of weights is associated with a respective partner of the plurality of partners (106);
receiving, by the at least one processor (112a), the plurality of customer requests associated with the plurality of customers (102);
generating, by the at least one processor (112a), distribution data based on the received plurality of customer requests and the computed plurality of weights, wherein the generated distribution data indicates that the plurality of customer requests is mapped to the plurality of partners (106); and
processing, by the at least one processor (112a), the plurality of customer requests based on the generated distribution data.
12. The method as claimed in claim 11, wherein computing the plurality of weights for the at least one customer segment further includes:
determining, by the at least one processor (112a), target capital data associated with the plurality of partners (106) for the at least one customer segment based on the acquired partner data;
computing, by the at least one processor (112a), total capital data associated with the plurality of partners (106) for the at least one customer segment based on the determined target capital data; and
computing, by the at least one processor (112a), the plurality of weights associated with the plurality of partners (106) for the at least one customer segment based on the determined target capital data, the computed total capital data, and the acquired first disbursed data.
13. The method as claimed in claim 11, wherein generating the distribution data further includes:
normalizing, by the at least one processor (112a), the computed plurality of weights;
storing, by the at least one processor (112a), the normalized plurality of weights in an array in a specific order;
executing, by the at least one processor (112a), a pseudo-random algorithm to generate a plurality of pseudo-random numbers for the plurality of customer requests; and
generating, by the at least one processor (112a), the distribution data based on the generated plurality of pseudo-random numbers and the array.
14. The method as claimed in claim 11, further comprising:
receiving, by the at least one processor (112a), a timing signal;
acquiring, by the at least one processor (112a), second disbursed data associated with the plurality of partners (106) for the at least one customer segment, wherein the second disbursed data is acquired based on the received timing signal; and
recomputing, by the at least one processor (112a), the plurality of weights associated with the plurality of partners (106) based on the acquired second disbursed data.
15. The method as claimed in claim 11, further comprising:
identifying, by the at least one processor (112a), a partner status of each partner of the plurality of partners (106); and
recomputing, by the at least one processor (112a), the plurality of weights associated with the plurality of partners (106) based on the identified partner status.