Abstract: Disclosed is a method and system for facilitating microfinance based on social credibility rating of an individual in the social network. The disclosure presents a relationship between microfinance value, acceptable error rate and size of the interacting social circle. It captures various social factors and personality traits of an individual to provide microfinance to a person, and further ensures return on investment based on current market value of money.
FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003
COMPLETE SPECIFICATION
(See Section 10 and Rule 13)
Title of invention: SYSTEM AND METHOD FOR MICROFINANCE OVER SOCIAL NETWORK
Applicant:
Tata Consultancy Services Limited A company Incorporated in India under The Companies Act, 1956
Having address:
Nirmal Building, 9th Floor,
Nariman Point, Mumbai 400021,
Maharashtra, India
The following specification particularly describes the invention and the manner in which it is to be performed.
TECHNICAL FIELD
[001] The present subject matter described herein, in general, relates to microfinance,
and more particularly to microfinance over a social network based on credit rating.
BACKGROUND
(002] Social networking has progressed aggressively in recent past, and social
interactions are a part of everyone's life today. As people evolve, the ways of social networking change. Currently, people are socializing using online social networks like Facebook, Twitter, Linked-in etc. With the help of these social interactions, people share their thoughts, likes-dislikes, etc. Premium services like lending and borrowing money may also be delivered via social interaction platforms. Commonly, money exchange is observed only among closed groups.
[003] Current mobile world provides many applications for money transactions i.e.
mCommerce. These mCommerce applications provide common facilities such as debit, credit and transfer of money. Internet banking has also proved its usefulness over time. However, it has not evolved for microfinance to that extent. Particularly because, these transactions are majorly built on social relationships, and more significantly upon the social credibility between interacting groups.
[004] Further, social credibility among the society is not considered in the banking
system. To open a bank account one needs a reference from a current account holder in the same bank, which poses a formidable challenge for the existing systems to transfer money to these accounts easily. Social credibility changes as the time progresses, but this is not considered in the current banking system and neither there is consideration of any other social aspect of the individuals. Further, none of the prior art teaches any method of ensuring money repayment/debt recovery at existing market rates. In addition, none counts the fraudulent activities of the individuals or infers from his frequent visited locations, tweets or vocabulary.
SUMMARY
[005] This summary is provided to introduce aspects related to systems and methods
for facilitating microfinance based on social credibility, and the aspects are further described below in the detailed description. This summary is not intended to identify essential features
of the claimed subject matter nor is it intended for use in determining or limiting the scope of the claimed subject matter.
[006] In one implementation, the method of the present disclosure facilitates
microfinance by computing upon a processor dynamically varying microfinance value for multiple participants of social networking platform. The variability of the microfinance value is captured by computing initial microfinance value of the participant and a variability factor. The highest and the lowest microfinance values of each of the social networking platform is determined from the microfinance values along with a corresponding error rate. The social credibility of each participant is then evaluated from the microfinance value, from the set of attributes, and from social activity or microfinance activity or a combination thereof at periodic intervals. Further, profile status of each of the participant is maintained. Next, the participants are notified of any demand for microfinance amount from other participant of the social networking platform, referred as a borrowing participant. The other participants are presented upon their participant interface the microfinance value, the social credibility and the profile status of the borrowing participant, as a measure to estimate the social credibility of the borrowing participant. Eventually, the participant who is willing to lend the microfinance amount is facilitated with microfinance transaction along with debt recovery based on current market value of microfinance amount.
[007] In one other implementation, a system for facilitating microfinance comprises
of a main unit coupled to a database, wherein said main unit is configured to :
compute dynamically varying microfinance value of plurality of participants within one or more social networking platform based on a set of attributes of the participant at a given instant, wherein variability of the microfinance value is captured by computing initial microfinance value of the participant and a variability factor;
derive social credibility score of plurality of participants within one or more social networking platform, from the microfinance value, from the set of attributes, and at least in part, from social activity or microfinance activity or a combination thereof, upon interacting with a personality interference unit which is operative to extract personality traits of the participant; a fraud detection unit operative to detect fraudulent
activity of the participant; compute error rate corresponding to each of the social networking platform;
facilitate microfinance amount transaction within the social networking platform upon interacting with a loan management unit that is operative to handle the microfinance activity while coordinating with the fraud detection unit, by notifying the participants of any demand for microfinance amount from a borrowing participant; facilitating at least one participant interested in lending the microfinance amount to the borrowing participant, in debt recovery based on current market value of said microfinance amount.
The system further comprises of a database that is operative for storing microfinance value, social credibility score, social activity, microfinance activity and other profile related information of the each participant present with the social networking platform.
BRIEF DESCRIPTION OF THE DRAWINGS
[008] The detailed description is described with reference to the accompanying
figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the drawings to refer like features and components.
[009] Figure 1 illustrates an overall architecture of the system, in accordance with an
embodiment of the present subject matter.
[0010] Figure 2 illustrates a flow diagram for facilitating microfinance over a social
network, in accordance with an embodiment of the present subject matter.
DETAILED DESCRIPTION
[0011] System and method for social credibility based microfinance over a social
network are described. The present subject matter further discloses a credibility rating calculation based on various social factors, and debt recovery based on money inflation-deflation rate. In particular, fraudulent activities of all those participating in social networking based transactions are tracked and considered before lending the microfinance amount. This
helps to take decisions regarding whom to lend the amount and whom not to, apart from acting appropriately for getting money repayment from the borrower within stipulated time.
[0012] The proposed system and method computes social credibility rating as the
weighted average of microfinance values of each person present in the social circle and their popularity in the social network in a particular duration. The relationship between microfinance value, acceptable error rate and size of the social circle is derived for computing the social credibility rating. Furthermore, the system and method enables debt recovery based on current market value of money within stipulated time.
[0013] While aspects of described system and method for enabling microfinance over
a social network may be implemented in any number of different computing systems, environments, and/or configurations, the embodiments are described in the context of the following exemplary system.
[0014] Referring now to Figure 1. an overall architecture of the system 100 for
enabling microfinance over a social network based on social credibility is illustrated, in accordance with an embodiment of the present subject matter. In one embodiment, the system 100 computes microcredit value for a person based on various factors and set of attributes like size of social network, credit rating, time, social activity, microfinance activity etc. In another embodiment, the system 100 determines personality traits of each participant of the social networking platform. In yet another embodiment, the system 100 facilitates debt recovery from the participant borrowing the microfinance amount based on current market inflation-deflation rates.
[0015] Although the present subject matter is explained considering that the system
100 is implemented upon a combination of inter-related modules implemented upon on a server, it may be understood that the system 100 may also be implemented in a variety of computing systems, such as a laptop computer, a desktop computer, a notebook, a workstation, a mainframe computer, a server, a network server, and the like. It will be understood that the system 100 may be accessed by multiple participants of one or more social networking platforms through one or more participant device interfaces 102(a), 102 (b)....102(n), collectively referred to as participant 102 hereinafter, or applications residing on the participant devices 102. Examples of the participant devices 102 may include, but are
not limited to. a portable computer, a personal digital assistant, a handheld device, and a workstation. The participant devices are communicatively coupled to the system 100 through a network 104 (not shown in the Figure).
[0016] In one implementation, the network 104 may be a wireless network, a wired
network or a combination thereof. The network 104 can be implemented as one of the different types of networks, such as intranet, local area network (LAN), wide area network (WAN), the internet, and the like. The network may either be a dedicated network or a shared network. The shared network represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like, to communicate with one another. Further, the network may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, and the like.
[0017] Broadly, the system 100 comprises of a main unit 106 inter connected to
plurality of other units to interact with the participant device. The main unit 106 is a brain of the system 100 and makes all decisions. The unit 106 handles the calculations related to microfinance value, upper bound and lower bound microfinance value, error rate, etc., each of which shall be discussed in detail in later sections of the document. The personality interference unit 108, of the system 100, is configured to extract personality traits of the participant 102 of the social networking platform(s) by using Natural Language Processing (NLP) technique. The personality of the participant 102 is determined from participant's vocabulary, tweets, likes, comments, status updates, etc. It also tracks participant's geographical location periodically and captures the pattern. The unit 108 farther tracks participant's geographical location periodically and captures the pattern. Another constituting unit of the system 100, is a fraud detection unit 110 that is configured to detect fraudulent activities of a participant 102 based on various factors such as increasing credit rating based dead accounts, circular trade, etc. Based on these factors trust-rating changes which affects participant's credit rating. The loan management unit 112 is functional to handles microfinance related activities of the participant 102. This includes both payment made to other participant device/borrowing participant and debt recovery therefrom based on current market inflation-deflation rates. The system 100 stores the computed microfinance value, social credibility score, social activity, microfinance activity and other profile related
information of the each participant 102 present within the social networking platform, in a database 114. The main unit 106 coordinates with the database 114 to update profile status of the participants 102 for assisting in decision making with regard to lending of microflnance amount to the demanding borrowing participant 102. In an embodiment, the main unit 106 generates a color coded profile of each of the participant 102 based on payment schedule to remind borrower for repayment. Subsequently, the other participants 102 get an alert whether to lend the amount thereto.
[0018] In one embodiment, the system 100 may include at least one processor upon
which various constituting units of the system 100 are implemented, an input/output (I/O) interface, and a memory. The at least one processor may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the at least one processor is configured to fetch and execute computer-readable instructions stored in the memory.
[0019] The I/O interface may include a variety of software and hardware interfaces,
for example, a web interface, a graphical participant interface, and the like. The I/O interface may allow the system to interact with a participant directly or through the participant devices 102. Further, the I/O interface may enable the system 100 to communicate with other computing devices, such as web servers and external data servers (not shown). The I/O interface can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example. LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. The I/O interface may include one or more ports for connecting a number of devices to one another or to another server.
[0020] The memory may include any computer-readable medium known in the art
including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. The memory may include constituting units of the system viz-a-viz main unit 106, personality interference unitl08, fraud detection unit 110, loan management unit 112. and a database 114.
[0023] The aforementioned units include routines, programs, objects, components,
data structures, etc.. which perform particular tasks or implement particular abstract data types. In one implementation, the units may include main unit 106, personality interference unitl08. fraud detection unit 110. loan management unit 112. and a database 114. The other units may include programs or coded instructions that supplement applications and functions of the system 100.
MAIN UNIT 106
[0022] Re-referring to Figure 1, a detailed working of the main unit 106 along with
the working of other components of the system 102 is illustrated, in accordance with an embodiment of the present subject matter. In one implementation, the main unit 106 computes microfmance values associated with each participant in a circle based on a relation between the microfinance value, the size of the social network and the corresponding error rates. The derivation of the relation discussed in detail in later sections of the document. Social networking sites like Facebook, Twitter, Linkedln, Google+, etc. have social circles, which put participants in different social circles like- circles of close friends, office friends, residential building groups, acquaintances, etc. The main unit 106 computes the microfinance value for every social circle since the activities, the people and their importance in that social circle is varies from one platform to the other.
[0023] In one implementation, the main unit 106 may access participant devices 102
directly to interact therewith and present thereupon microfinance value of the social circle, associated error rate, social credibility of the participants 102, their profiles and the like. Examples of social circle may include social networking websites, feedback/review collection websites, and blogs. It should be noted that the terms "social circle", "social media" and "social networking platform(s)" has been used interchangeably within the document.
[0024] The participant 102 may provide a list of social circle at the time of registration
and such list of social circle may be stored in the system database 114. Further, the participant 102 may also permit the system 100 for mining the profiles/records from websites named in the list of social circle. Based upon the profile the main unit 106 computes microfinance values of each of the participant 102, the upper bound and lower bound of the microfinance for each of the social circle, inputs participant profile and social activity related details
retrieved from the other units of the system 100 into database 114, keep atomicity, calculate the error rate, etc,
[0025] Each participant from each social circle represents different personality traits.
These personality traits are derived by the personality interference unit 108, discussed in the following section. Depending upon these factors, the main unit 106 computes error rate s based on the microfinance value of respective social circle and size thereof. This intimate the participant of the error factor present in the circle. Thus, the participant 102 is enabled to make decision whether to microfinance i.e. microfinance amount or not. This is a practical value of microfinance. However, the error rate may change. The main unit 106, nevertheless, improves the value of error rate automatically based on the observations from number of microfinance transactions, which makes the system more reliable and efficient.
[0026] Furthermore, the main unit 106 computes credit rating for each participant 102
of the system 100. The credit rating calculation is explained in later part of the document. The main unit 106 increases credit rating of the participant 102 based on the microfinance amount given out to others. More the participant lends microfinance amount, the higher is his credit rating.
[0027] Additionally, any participant can recommend any new participant to the system
100 based on the trust rating given to the new participant. If the new participant found to be a fraud participant by the fraud detection unit 110, then the credit rating equivalent to trust rating is deducted from the account of the participant who had introduced the new participant to the social circle. Accordingly, the result is updated in the database 114.
[0028] The main unit 106 also interacts with the loan management unit 112 to receive
therefrom inputs regarding payment schedule of the borrowing participant. Consequently, the main unit 106 sends notifications to the borrowing participant. After the predefined repayment time has elapsed, the unit 106 activates profile coloring function. Thus, it asks borrowing participant to repay the microfinance amount as soon as possible to extemporize his profile status, as viewed to others on the social networking platform.
[0029] Every participant present on the social network has an associated profile,
which reflects his popularity and goodness on the social network. Based on the time elapsed since scheduled repayment, the main unit 106 activates the profiling coloring function. The
function targets the borrower's profile, which changes the color of profile. Regularly after certain duration "X" by "X" number of pixels change their color. For example, the color of particular set of pixels may change from Pink to Red to Dark Red as the credibility of the profile decreases. Even if the borrower does not repay, then the number of pixels with such color format increases. After certain duration the main unit 106 sends notifications to other participants 102 and warns them to not to lend money to the particular participant.
[0030] It is important to note that, the credit rating of a participant is limited to that
circle only. It means a participant X may have high credit rating in a circle S, but the same user may not have high credit rating in other social circle. Thus, the participant has to gain credit rating in the social circle. This same principle is also applicable with microfinance. Every user has to gain microfinance in a social circle and it is different for different social circles.
PERSONALITY INTERFERENCE UNIT 108
[0031] As mentioned before, the participant 102 may permit the system 100 for
mining the profiles/records from websites. The personality interference unit 108 of the system 100 performs the task of mining the records of the participants from the social networking platform. Such records are retrieved from participant's social activity reflected in the posts, updates, articles, and comments provided by the participant on the social networking platform. It may be understood that the social activity information of the participant may also be obtained from profiles of other participants known to the said participant. Further, it may be understood that the participants 102 may express their emotions such as, happiness, sadness, excitement, and patriotism in forms of status updates, comments, and posts on the social media
[0032] The personality interference unit 108 monitors following activities of the user
as: a) Social activity and Vocabulary and; b) Geographical Location.
[0033] A) Social activity and Vocabulary: The participants of social networking
platform are always engaged into the activities such as status updates, tweets, likes, comments, etc. NLP based personality inference unit 108 extracts all the nouns, verbs, adjectives and adverbs from the social activities described above and categorize them to various containers. There are four large sized containers, which take nouns, verbs, adjectives
and adverbs. Each of these containers contains sub-containers, which describes the words easily to provide abstraction. The sub-containers are created such that the words, which are put into these containers, are easily described. The purpose of this categorization is to categorize the participant according to the vocabulary. Initially these containers are empty. As the time elapse, more and more number of words is added to the categories. According to the frequency of use of the words, the personality interference unit 108 shows some major categories under which the participant falls.
[0034] The categorizations of words takes place in bottom to top fashion and
accordingly the categories are created. E.g. the participant 102 enters words such as "happy", "glad", "fortunate", "cheerful", etc. many times in his social interaction. The personality interference unit 108 assigns these words to a category called "Happy". Alternately, if the participant enters words such as "sorry", "sorrowful", "sad", "woeful", etc., the unit 108 adds these words under a "sad" category. Depending upon the frequency of words used by the participant, the unit 108 arranges the categories in descending order of the frequency of words. This helps the participant to identify the typical nature of the participant. If the participant is sad for most of the time, then the lender decides whether to lend this "sad" participant or not. Some of the categories presented in the list may have antonyms like first item in the list is "Happy" and second item as "Sad". The lender has to make the decision depending upon his/her cognitive ability.
[0035] Further, the personality interference unit 108 evaluates the popularity and
goodness factor of the participant. The unit 108 estimates the popularity of the participant based on the likes, comments, and re-tweets made by other participants present in the social circle. This suggests the popularity of the participant, which is also used while calculating the microfinance value and credit rating of the participant 102 by the main unit 106.
[0036] B) Geographical Location: Geography based inference technique is also an
important part of personality interference unit 108. Social networking sites provide facility to add location of the participant 102. They also provide tagging facility, which further assists in determining the location of the participant 102. If the location is not available, then the unit 108 searches for noun, if any, from the status update or tweet to find out the location of the participant 102. The personality interference unit 108 has a preloaded database, which
consists of weight factor for all the locations on a scale of 1 to 100. These weights are assigned according to the importance of the place, type of people visit/stay, etc. For example, hotel Taj can be accorded a higher weight, and slum a lower weight etc.
[0037] The personality interference unit 108 tracks timings of the participant at
various locations and records his latitude-longitude dimensions, location words to its database along with the timings. The unit 108 also derives a pattern of participant occurrence at various locations. If the participant shows a regular occurrence pattern, then the score of the destination accorded a lower weight is considered. For example, if a participant happens to travel from a low weightage place like a slum to a high weightage place like a luxury hotel, then the score corresponding to that of the slum is taken into account for that participant. The consolidation of the weight is done periodically-say every day, every fortnight, every month, or every 6 months. Thus, it is a continuous process to find out the location of the participant. The score of the participant is calculated every day and average of the scores is taken. In an embodiment, the score obtained for the participant is placed on a scale of 10. It is added to the database and is used to evaluate participant's social status. Based on both geography based inference technique, and vocabulary based inference technique, popularity and goodness of the participant is derived.
FRAUD DETECTION UNIT 110
[0038] The fraud detection unit 110 continuously monitors all microflnance-based
transactions of all the interacting participants. The unit 110 monitors activities of other participants, which are directly associated with the said participant 102. This includes finding dead accounts, practice of circular trade or any other fraud to contribute in computing the social credibility of the participant by the main unit 106.
[0039] For instance, in case of dead accounts, which are actually the inactive accounts
and which the participant 102 may use for increasing his credit rating by involving in various microfinance transactions, the unit 110 is configured to detect and annul such accounts. These dead accounts always have a pattern- they are either inactive or active with regular pattern. As all the participants are registered and permits mining of their social network details to the system 100. the system 100 continuously monitors the social networking activities of all the participants 102.
[0040] The dead accounts can be identified by: a) determining the microfinance
activity of the participant, and b) the number of accounts associated with the current participant account.
[0041] A) Microfinance activity of the participant: This helps to find out whether the
participant is inactive for a long time. If the social networking activities associated with an account are zero, then it implies that the account is dead. There may also be a situation wherein a constant endeavor is made to spend some time on the social network to prove the account is not dead. Thus, the fraud detection unit 110 takes note of time 't\ which is used to find the fixed usage of the account. In addition the unit 110 also finds whether different or same set of participants visit the profile of the suspicious account holder. If a constant number of participants and same participants visit the suspicious account, then the account is declared dead.
[0042] B) Number of accounts associated with the current participant account: If there
is no account, which gets added to the account, there might be the case that some account might get added, but if the activities of these accounts are also zero, then the accounts are considered dead accounts.
[0043] Similarly, the fraud detection unit 110 detects the participants for circular
trade. Circular trade is a trade in which a circular microfinance takes place. This means the participant exchange microfinance to increase credit rating and bluff other participants present in the social circle. To detect circular trade, the fraud detection unit 110 monitors microfinance transactions of all the participants in the circle. The participant can exchange microfinance with each other, but if this exchange takes place more than once in a particular duration, then the credit rating of the participant does not increase. This is found out for a specific duration. On the contrary, if the microfinance exchange takes place at once in a defined period, then the credit rating increases. However, if another transaction takes place between the same participants, then credit rating is reduced to the original rating.
[0044] This circular trade can take place between as many as all the participants
present in the circle. If such transaction takes place more than once during the predefined period, then credit rating remains same.
[0045] Further, the fraud detection unit 110 is entrusted with a task of assigning the
trust ratings to a new participant by the existing user of the social circle, and communicating the trust ratings to the main unit 106. In one implementation of the present system 100, every participant can introduce a new participant to the system 100. However, the existing participant has to give trust rating to the new participant. If the trust rating of the new participant is less than the predetermined trust rating for the group, then the new participant will not be placed in the social circle.
[0046] The fraud detection unit 110 works on the microfinance and introducing a
participant requires a trust rating to be accorded to a new participant, wherein the trust rating is a rating for which each of the existing participants agrees upon. If the new participant is found to be a fraud or having a dead account, then the credit rating of the referral participant goes down. This is introduced in the system so that existing participant introduce new participant only if they have trust of that participant. Thus, every participant gives trust rating to a new account with some responsibility. This will help not only fraud participant to stay away but also honest person, entrepreneur to get benefit from microfinance.
[0047] Referring to the diagram given below wherein a set of participants connected
in a social circle are represented, an effect of trust rating and circular trading is shown.
[0048] The diagram of social circle given above is a graph G = (V, E) consisting of set
of objects V = {A, B, C, D, E, F, G, H, I, J, K, L} called participants, and set of edges E. In this graph, node E links three complete graphs. Considering a complete graph, if a new node is to be added to the complete graph with vertices V ={A, B, C, D. E}, five edges will be required to make it a complete graph. Thus, as a new participant gets introduced in a social circle, all the existing participants get connected to it. Hence, the trust on that new participant is important, which is equivalent to the credit rating of the user. If the new participant happens to be a fraud participant, then credit rating equivalent to trust rating decreases from the referral participant's credit rating. Therefore, every participant gives trust rating to any new participant accordingly.
[0049] Jt is important to note that the credit rating of a participant is limited to a
particular circle only. It means a participant E may have high credit rating in a circle SI, but the same user may not have high credit rating in other social circles S2 or S3. Thus, the user
has to gain credit rating in the other social circles to attain credible social rating and eventually obtain microfinance from those circles.
LOAN MANAGEMENT UNIT 112
[0050] The loan management unit 112 broadly comprises of two important sub units
namely loan payment and loan recovery sub units. One general embodiment does not have enable the loan management unit 112 to have a direct access to database 114, which contains all the information related to the participant. Whenever the participant decides to lend microfinance to a participant in the social circle, the unit 112 transmits signal to the main unit 106 to make an entry in the database 114 for the transacted microfinance amount.
[0051] Loan Payment: Loan Payment sub unit controls the functions related to loan
payment. It takes the microfinance values, error rate, personality traits and other set of attributes, from the database 114 for each participant and presents it onto other participant devices 102. The main unit 106 has already calculated the microfinance value for each participant and the error rate. Whenever a participant wants to lend microfinance, loan payment sub unit requests the main unit 106 to make micropayment. This sub unit is however only concerned with microfinance payment.
[0052] An important task of loan payment sub unit is to get the fraudulent activities of
the borrowing participant from the fraud detection unit 110. The unit 310 reports to the loan management unit 112 whether the participant is engaged in fraudulent activities or not. This helps lenders to make decisions.
[0053] Loan Recovery: Loan Recovery sub unit is configured to counts the days for
which a participant has requested for a microfinance repayment. The basic philosophy behind loan recovery is to obtain from the borrowing participant, the interest associated with the given microfinance amount based on existing inflation-deflation rates in the market. Thus, the borrowing participant has to pay principle amount along with the interest. This interest can also be negative depending upon the market value of money. If the market value of money is higher that the market value at the time loan was taken, then the borrowing participant has to
pay an amount multiple of the principle, rate difference. The lender is expected to receive principal amount plus the interest, which is calculated as follows:
Interest I = P. {Rcurr-Ri)
Where I is the interest
P is principal amount
Rcurr is the current inflation rate
Ri is the initial inflation rate i.e. when a borrowing participant takes loan
[0054] The loan recovery sub unit calculates the recovery amount according to current
market value of money. The above interest rate is applicable if the amount is returned on or before the expected time period. In case, the borrowing participant fails to repay in the stipulated time, then the interest is calculated as:
Interest I = P. (Rcurr-Ri).T
Where T is time in months
Time is preferably taken in months because usually the microfinance amount is low. After the stipulated time has elapsed, the interest is taken only as a positive value. This means that even if the current inflation rate is lower than the inflation rate at the time microfinance amount was taken, the borrowing participant has to pay the interest.
The total amount that has to be paid is equal to: Total T = P+I
Now. if the debt recovery period i.e. stipulated time expires and still the borrowing participant does not return money, the loan management unit 112 requests the main unit 106 to send the notifications to the borrowing participant. The unit 112 also requests the main unit 106 to change the borrowers profile color scheme till the borrowing participant returns money. Consequently, this also affects the credit rating of the borrowing participant as the unit 112 sends request to main unit 106 to reduce the credit rating of the borrowing participant depending upon the time elapsed.
[0055] Referring now to Figure 2. a method 400 for facilitating microfinance utilizing
the aforementioned units of the system 100 is shown, in accordance with an embodiment of
the present subject matter. The method 400 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, functions, etc., that perform particular functions or implement particular abstract data types. The method 400 may also be practiced in a distributed computing environment where functions are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, computer executable instructions may be located in both local and remote computer storage media, including memory storage devices.
[0056] The order in which the method 400 is described is not intended to be construed
as a limitation, and any number of the described method steps can be combined in any order to implement the method 400 or alternate methods. Additionally, individual steps may be deleted from the method 400 without departing from the spirit and scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof. However, for ease of explanation, in the embodiments described below, the method 400 may be considered to be implemented in the above described system 100.
[0057] At step 402, a dynamically varying microfinance value of each participant of
the social networking platform may be determined. In one implementation, the microfinance value and acceptable error rate for each of the social networking platform is computed by the main unit 106 based on pre-derived relationship amongst them.
[0058] Relation 1: Sa
Where S is the size of social circle
u. is the microfinance amount
According to the above relation, as the size of social circle increases, the microfinance amount decreases. The above relation holds true when one affords to give a constant amount and number of borrowing participants are increasing. The size of social circle S can also be depicted as the size of borrowers. As the size of social circle increases, the size of borrowing participants may also increase.
E.g. If a friends circle has few members in a circle then a person can give higher micro finance to needy friends. Nevertheless, if the circle is large, then one cannot give the same amount to many. One can give an amount x to a borrower, but the amount divides if more borrower wants microfinance.
[0059] For a social circle with N number of friends, the system 100 calculates a base
value or an initial value of microfinance for a social circle and microfinance values for each participant of the social network. These values are the lower and upper limit of the microfinance for a participant. These values suggest the capacity of a participant to return the debt. Sometimes, even if participant act appropriately, they fail to recover their money from the borrowing participant. The system takes this as an error rate.
[0060] The error rate depends upon the size of social circle. The underlying principle
for this is if the number of participants in a social circle increases, diversity increases. This diversity is in terms of location, personalities, availability at a place, and many more, which affects the error rate.
[0061] Relation 2: S aє
Where S is the size of the social circle
є is the error value
According to the above relation, as the size of the social circle increases, the error rate of debt recovery increases.
[0062] For instance, consider a social circle named as "Cubicle Mates Circle" with
only two members X and Y. They come to office everyday and work. They can exchange money easily as they stay together for a long time. Thus, even if X gives money to Y and Y forgets or cannot pay due to some circumstances/reasons; still the error rate is very low as X can remind Y anytime. Alternately, in another scenario the social circle may be formed of participants of a conference who formed a group of 30. Members of this group might be good friends and close to each other. Still, money recovery becomes pain as one cannot travel far places just to collect microfinance like Rs. 50, or one may even forget to return such a small money after borrowing. Thus, error rate increases.
[0063] In addition to this, in a social circle if a lender gives microfinance to many
participants, then it becomes difficult to track every borrower for getting the money back, which introduces higher error rate.
[0064] From Relation 1 & Relation 2, Relation 3 can be drawn as:
Relation 3: є a
Where 8 is the error value
μ is the microfinance amount
[0065] The above derived Relation 3 suggests that the error rate decreases with
increase in microfinance. This relation hold true for each individual in real world. People become more conscious as the money given to any person increases. This means that as people give more microfinance. they become more conscious, attentive for their money. For example, one can give a microfinance amount Rs. 10 and forget, but if Rs. 1000 is given as a microfinance, then one has to remember to get the money back.
[0066] Based on above derived three relations, the microfinance value for each
participant is computed.
Calculating μ(step 402)
[0067] In the microfinance system, the value of microfinance u changes from person-
to-person. As the system considers personality traits of every participant, it helps students, entrepreneurs who might not have high bank balance, but their thoughts; popularity among the group helps them get more microfinance from the group. The "likes" or goodness for the activities of a participant from the social circle helps him to get microfinance. This factor is calculated after regular duration and is based on previous score. The microfinance value of an individual is a function of "likes" and time.
[0068] μ = f(t,L)
Where t is a particular duration L is the "likes"
The duration t is a customized value for the system 100, which can be changed according to demand.
[0069] The microflnance value of any participant is a changing value depending upon
time and "likes"'. The microflnance value depends upon the initial social activity of the participant, which is determined from the popularity of a participant in the social circle. As the participant registers to the system, the system 100 starts monitoring social network activities of the participant. The system 100 considers various aspects to calculate the microflnance value of the participant. The system 100 does not want a participant to get affected by the irregularity in status updates, tweets, etc. Thus, it calculates initial activities of the user in an initial period i.e. activities after the user registers to the system. After this, the system checks the activities of the participant regularly after certain duration.
[0070] The initial microflnance valueu of a user U1 in a circle S1 is calculated as
[0071] Condition: # of posts > 0
If#ofposts = 0,then μ(UI) = 0 After the initial microflnance value is calculated, all further values of calculated as
μ(U1) = previous μ(U1) ± ∆
[0072] The reason behind adding A is that a participant may not be active during all
the time. The microflnance value should not get affected much if the participant is not active for some time. However, the microflnance value shall change because of the inactive condition in a particular duration. The value of A gets affected if a large number of users are present in the circle or a larger number of people are following a certain group and the user is inactive in that group.
[0073] If a participant is inactive during certain duration, the value of A is subtracted
from the initial microfinance amount. If the participant is active during certain duration, the value of A is added to the initial microfinance amount.
Calculating Upper bound and lower bound value of microfinance
[0074] People with different traits form a social network. Based on their performance
in the social network and their credibility their microfinance value changes. This microfinance value is used to calculate upper bound and lower bound of the microfinance value of any participant. The value of lower bound of microfinance is the lowest value of microfinance in the social network. The upper bound of the microfinance is the microfinance value of the participant. However, the lender has to decide the amount of microfinance he/she can lend.
[0075] Assuming that there is social network among 10 people having microfinance
values as μ1 μ2, μ3 μ4, μ5, μ6, Μ7, Μ8, μ8, μ10- The system finds out the lowest value of the microfinance among the group, which becomes microfinance value μ of the group. This value suggests the minimum amount of microfinance, which can be lent and which has a specific error rate s. This error rate is the lowest error rate among the group. The upper bound of the microfinance is the maximum microfinance amount of each participant.
Calculating Error Rate ε (Step 402)
[0076] From Relation 1, Sa
From the above relation. S.Μ=K Equation 1 (where k1 is a constant)
[0077] From Relation 2, S a s
From the above relation, = k2 Equation 2 (where k2 is a constant)
[0078] From Relation 3, sa
From the above relation, ε.μ=k3 Equation 3 (where k3 is a constant)
[0079] Combining equations 1, 2 and 3
Upon Simplifying the above equation,
[0080] Simplifying again.
k1.k2.μ.ε2 + k2.k3[S.μ-3.k1].ε+kl.k3S = 0
[0081] This equation is used to calculate the value of £ as the size of a social circle is
fixed and the microfinance value is already calculated. Thus, the value of ε is calculated as
[0082] From the above formula two values for e are obtained. Out of these two values,
the lower value provides a more useful insight, and hence will be considered. The value of e is calculated as :
[0083] In the above formula, the value of S and μ is already known. The value of k|,
k2 and k3 is a known constant whose value can be calculated based on three observed and standard value of S, u and ε. The system 100 gets the standard values of S, μ. and ε as an input and calculates k1 k2 and k3. The standard values of S, μ and £ are the observed values for certain set of participants.
[0084] For example the system 100 finds that for S1 number of users in a circle with
microfinance value μ1 gives ε1 error. Considering these values the value of k1, k2, and k3 is calculated. After the system 100 finds this value, for any value of S, p the system 100 can calculate the value of e.
[0085] If the system observes from a number of transactions that the value of error
rate is different, then system updates the value of k1, k2, and k3 according the result obtained. This makes the system more reliable and efficient. This cycle continues from time to time based on the observations from number of transactions. Thus, the system improves the value of error rate E automatically.
Calculating Social Credibility (Step 404)
[0086] The credit rating helps to understand the credibility of a participant, which
helps others for microfinance decisions. Every participant has a different microfinance value and this microfinance value is used to calculate credit rating of a participant. The credit rating of a participant Uj is the summation of the product of "like" factor of each participant Ui to Uj and microfinance values of each μi. This can be written as
The value of "like" factor of Ui to Uj which is Li is calculated as
The # of likes from Ui to Uj are written as : L(Ui, Uj) = # of likes from Ui to Uj. Thus, the likes of Li are obtained as:
[0088] This "like" factor gives the weight of "likes" of i for j. Thus, it helps to obtain
weighted average of the credit rating of a participant. The value of Li lies between 0 and 1. If a participant does not "like" any of the activities of another participant, then the value of Li becomes zero. If all the participant "like" all the activities of another participant, then the value becomes one. However, the summation of L,S remains less than or equal to one.
[0089] Upon computing the microfmance value, error rate and social credibility of the
participants and the interacting social network by the main unit 106, notification is send to the system 100 whenever the participant 102 is in need of microfinance amount (As shown in step 406). Next, the fraud detection unit 110 detects the borrowing participant of any fraudulent activity, as in step 408. The loan payment sub unit of loan management unit 112 now collects credit rating, microfinance value, profile status of the participant 102 for determining if the microfinance amount can be lend out to the borrowing participant, as shown in step 410. Concurrently, the main unit 106 increases the credit rating of the participant for his initiative to lend out the microfinance amount (shown in step 412). The borrowing participant is lended with a microfinance amount, but with a clause to make the repayments within a stipulated time period, until which the loan management unit 112 of the system 100 waits, as indicated in step 414.
[0090] Loan Recovery sub unit of the loan management unit 112 counts the days for
which a participant has requested for a microfinance repayment, beyond which the loan management unit 112 starts sending notification to the borrowing participant of the scheduled repayment and repayment amount which is based on existing inflation-deflation rates in the market (shown in step 416). Thus, the borrowing participant has to pay principle amount along with the interest. The time that is lapsed in making such repayment is tracked by the main unit 106, which coordinates with the loan management unit 112 to change the profile of the borrowing participant based on a color-coded scheme (step 418). As shown in step 420 and as mentioned above, the repayment amount is calculated by the loan recovery unit 112 based on the current market value of the money. Accordingly, the main unit also modifies (increase/decrease) the credit rating of the borrowing participant based on time taken to repay the borrowed microfinance amount (as shown in step 422.)
[0091] The present disclosure thus provides a low cost alternative to determine social
credibility of the participant. Additionally, the present system and method helps to build social bond among the users by enabling transacting microfinance amount whenever needed.
WE CLAIM:
1) A computer implemented method for facilitating microfinance, comprising:
computing, by at least one computer processor, dynamically varying microfinance value for plurality of participants within one or more social networking platform at a given instant, wherein variability of the microfinance value is captured by computing initial microfinance value of the participant and a variability factor thereafter;
determining from the microfinance values of plurality of the participants, lowest and highest microfinance values of the social networking platform, along with a corresponding error rate;
evaluating the social credibility of each of the participant from the microfinance value, from set of attributes, and at least in part, from social activity or microfinance activity or a combination thereof at periodic intervals;
maintaining a profile status of the each participant;
notifying to the participants, of any demand for microfinance amount from a borrowing participant;
presenting upon an interface of the participants, the microfinance value, the social credibility and the profile status of the borrowing participant; and
facilitating at least one participant interested in lending the microfinance amount to the borrowing participant, in debt recovery based on current market value of said microfinance amount.
2) The computer implemented method of claim 1, further comprises computing a trust score for a new participant to the social networking platform, wherein the new participant is a referral from existing participants of the social networking platform.
3) The computer implemented method of claim 1, wherein the set of attributes of the participant comprises of personality traits, popularity and goodness attained on the social networking platform during a predetermined time interval, and the like or a combination thereof.
4) The computer implemented method of claim 3, wherein the personality traits
are extracted using
natural language processing technique based on vocabulary, tweets, likes, comments, status updates and similar social activity on the social networking platform, or
geographical location based on latitude-longitude coordinates of the participant, timing and pattern of occurrence of the participant therein, or
a combination thereof.
5) The computer implemented method of claim 1, wherein the set of attributes are periodically computed, wherein an initial social activity of the participant is recorded, said initial social activity being the social activity immediately following registration of the participant on the social networking platform.
6) The computer implemented method of claim 1, wherein the social activity refers to at least one activity on the social networking platform, comprising of status updates, tweets, likes, comments, or a combination thereof.
7) The computer implemented method of claim 1, wherein the initial microfinance value of the participant is computed based on the goodness attained by the participant relative to number of posts made on the social networking platform during the initial social activity thereof.
8) The computer implemented method of claim 1, wherein the variability factor is measured considering size of social network of the participant within the social networking platform, the initial microfinance value and duration following the initial social activity of the participant
9) The computer implemented method of claim 1, wherein the variability factor is measured intermittently over a period following the initial social activity of the participant to indicate active or inactive state of the participant.
10) The computer implemented method of claim 9, wherein for the participant state determined as inactive, subtracting the variability factor from the initial microfinance value.
11) The computer implemented method of claim 9. wherein for the participant state determined as active, adding the variability factor to the initial microfinance value.
12) The computer implemented method of claim 1, wherein the social credibility of the participant enhances on lending the microfinance amount.
13) The computer implemented method of claim 1. wherein the social credibility diminishes whenever
the participant state is determined inactive for a period exceeding the preset time, or same set of other participants within the social network are identified as visiting the participant profile, or
the microfinance activity amongst the participants involves a mere exchange of the microfinance amount, or a combination thereof.
14) The computer implemented method of claim 1, wherein the social credibility of the participant is specific to each of the social networking platform, and optionally varies from the one social networking platform to other.
15) The computer implemented method of claim 1, wherein the error rate is determined from a plurality of factors including the size of the social network, the microfinance values, diversity in the set of attributes of the participant and the like or a combination thereof.
16) The computer implemented method of claim I. wherein the profile status is determined from color scheme exhibited by the profile of the participant wherein said color scheme is updated based on
the social activity of the participant, or
the microfinance activity of the participant, or
frequency of the participant in lending the microfinance amount, or
ability of the borrowing participant to make repayments within destined time, or
a combination thereof.
17) The computer implemented method of claim 1, wherein the debt recovery includes recovery of principal microfinance amount and interest associated therewith, wherein said interest rate is computed based on the current market value of the microfinance amount and duration exceeding stipulated period of repayment.
18) A system for microfinance, comprising:
a main unit, implemented upon a processor, coupled to a database, wherein said main unit is configured to :
compute dynamically varying microfinance value of plurality of participants within one or more social networking platform based on a set of attributes of the participant at a given instant, wherein variability of the microfinance value is captured by computing initial microfinance value of the participant and a variability factor thereafter;
compute error rate corresponding to each of the social networking platform;
derive social credibility score of plurality of participants within one or more social networking platform, from the microfinance value, from the set of attributes, and at least in part, from social activity or microfinance activity or a combination thereof, upon interacting with:
a personality interference unit operative to extract personality traits of the participant;
a fraud detection unit operative to detect fraudulent activity of the participant;
facilitate microfinance amount transaction within the social networking platform upon interacting with:
a loan management unit that is operative to handle the microfinance activity while coordinating with the fraud detection unit, by notifying the participants of any demand for microfinance amount from a borrowing participant; facilitating at least one participant interested in lending the microfinance amount to the borrowing participant, in debt
recovery based on current market value of said microfinance amount; and
the database operative for storing microfinance value, social credibility score, social activity, microfinance activity and other profile related information of the each participant present within the social networking platform.
19) The system of claim 18, wherein the main unit further interacts with at least
one participant interface to present thereupon the microfinance value, the social
credibility and the profile status of the borrowing participant.
20) The system of claim 18. wherein the main unit is further configured to determine from the microfinance values of plurality of the participants, lowest and highest microfinance values of each of the social networking platform, along with the corresponding error rate.
21) The system of claim 18, wherein the main unit computes the error rate from a plurality of factors including the size of the social network, the microfinance values, diversity in the set of attributes of the participant and the like or a combination thereof.
22) The system of claim 18, wherein the set of attributes of the participant comprises of the personality traits, popularity and goodness attained on the social networking platform during a predetermined time interval, and the like or a combination thereof.
23) The system of claim 18, wherein the social activity refers to at least one activity on the social networking platform comprising of: status updates, tweets, likes comments, or a combination thereof.
24) The system of claim 18, wherein the main unit computes the initial microfinance value of the participant based on the goodness attained by the participant relative to number of posts made on the social networking platform during initial social activity thereof, wherein the initial social activity refers to the social activity immediately following registration of the participant on the social networking platform.
25) The system of claim 18, wherein the main unit measures the variability factor by considering size of social network of the participant within the social networking platform, the initial microfinance value and duration following the initial social activity of the participant.
26) The system of claim 18. wherein the personality interference unit extracts personality traits using:
natural language processing technique based on vocabulary, tweets, likes, comments, status updates and similar social activity on the social networking platform, or
geographical location based on latitude-longitude coordinates of the participant, timing and pattern of occurrence of the participant therein, or
a combination thereof.
27) The system of claim 1, wherein the fraud detection unit detects fraudulent
activity of the participant by monitoring plurality of factors comprising:
initial social activity or social activity of the participant,
frequency of participation in the social activity for determining active or inactive state of the participant,
nature of microfinance activity,
profile status, or a combination thereof.
28) The system of claim 18, wherein the social credibility of the participant
enhances on lending the microfinance amount, and diminishes whenever:
the participant state is determined inactive for a period exceeding the preset time, or same set of other participants within the social network are identified as visiting the participant profile, or
the microfinance activity amongst the participants involves a mere exchange of the microfinance amount, or a combination thereof.
29) The system of claim 18, wherein the loan management unit enables recovery of
principal microfinance amount and interest associated therewith, wherein said interest
rate is computed based on the current market value of the microfinance amount and duration exceeding stipulated period of repayment.
30) The system of claim 18, wherein the profile status is determined from color scheme exhibited by the profile of the participant, said color scheme being updated based on:
the social activity of the participant as determined by the main unit upon coordinating with the personality interference unit and the fraud detection unit, or
the microfinance activity of the participant, frequency of the participant in lending the microfinance amount, ability of the borrowing participant to make repayments within destined time, or a combination thereof as determined by the main unit upon coordinating with the loan management unit.
| Section | Controller | Decision Date |
|---|---|---|
| # | Name | Date |
|---|---|---|
| 1 | 1145-MUM-2013-US(14)-HearingNotice-(HearingDate-07-05-2021).pdf | 2021-10-03 |
| 1 | ABSTRACT1.jpg | 2018-08-11 |
| 2 | 1145-MUM-2013-Response to office action [12-04-2021(online)].pdf | 2021-04-12 |
| 2 | 1145-MUM-2013-FORM 3.pdf | 2018-08-11 |
| 3 | 1145-MUM-2013-FORM 26(6-5-2013).pdf | 2018-08-11 |
| 3 | 1145-MUM-2013-CLAIMS [26-07-2019(online)].pdf | 2019-07-26 |
| 4 | 1145-MUM-2013-FORM 2.pdf | 2018-08-11 |
| 4 | 1145-MUM-2013-COMPLETE SPECIFICATION [26-07-2019(online)].pdf | 2019-07-26 |
| 5 | 1145-MUM-2013-FORM 2(TITLE PAGE).pdf | 2018-08-11 |
| 5 | 1145-MUM-2013-DRAWING [26-07-2019(online)].pdf | 2019-07-26 |
| 6 | 1145-MUM-2013-FORM 18.pdf | 2018-08-11 |
| 6 | 1145-MUM-2013-FER_SER_REPLY [26-07-2019(online)].pdf | 2019-07-26 |
| 7 | 1145-MUM-2013-OTHERS [26-07-2019(online)].pdf | 2019-07-26 |
| 7 | 1145-MUM-2013-FORM 1.pdf | 2018-08-11 |
| 8 | 1145-MUM-2013-FORM 1(29-5-2013).pdf | 2018-08-11 |
| 8 | 1145-MUM-2013-FER.pdf | 2019-01-29 |
| 9 | 1145-MUM-2013-DRAWING.pdf | 2018-08-11 |
| 9 | 1145-MUM-2013-ABSTRACT.pdf | 2018-08-11 |
| 10 | 1145-MUM-2013-CLAIMS.pdf | 2018-08-11 |
| 10 | 1145-MUM-2013-DESCRIPTION(COMPLETE).pdf | 2018-08-11 |
| 11 | 1145-MUM-2013-CORRESPONDENCE(29-5-2013).pdf | 2018-08-11 |
| 11 | 1145-MUM-2013-CORRESPONDENCE.pdf | 2018-08-11 |
| 12 | 1145-MUM-2013-CORRESPONDENCE(6-5-2013).pdf | 2018-08-11 |
| 13 | 1145-MUM-2013-CORRESPONDENCE(29-5-2013).pdf | 2018-08-11 |
| 13 | 1145-MUM-2013-CORRESPONDENCE.pdf | 2018-08-11 |
| 14 | 1145-MUM-2013-CLAIMS.pdf | 2018-08-11 |
| 14 | 1145-MUM-2013-DESCRIPTION(COMPLETE).pdf | 2018-08-11 |
| 15 | 1145-MUM-2013-ABSTRACT.pdf | 2018-08-11 |
| 15 | 1145-MUM-2013-DRAWING.pdf | 2018-08-11 |
| 16 | 1145-MUM-2013-FER.pdf | 2019-01-29 |
| 16 | 1145-MUM-2013-FORM 1(29-5-2013).pdf | 2018-08-11 |
| 17 | 1145-MUM-2013-FORM 1.pdf | 2018-08-11 |
| 17 | 1145-MUM-2013-OTHERS [26-07-2019(online)].pdf | 2019-07-26 |
| 18 | 1145-MUM-2013-FER_SER_REPLY [26-07-2019(online)].pdf | 2019-07-26 |
| 18 | 1145-MUM-2013-FORM 18.pdf | 2018-08-11 |
| 19 | 1145-MUM-2013-DRAWING [26-07-2019(online)].pdf | 2019-07-26 |
| 19 | 1145-MUM-2013-FORM 2(TITLE PAGE).pdf | 2018-08-11 |
| 20 | 1145-MUM-2013-FORM 2.pdf | 2018-08-11 |
| 20 | 1145-MUM-2013-COMPLETE SPECIFICATION [26-07-2019(online)].pdf | 2019-07-26 |
| 21 | 1145-MUM-2013-FORM 26(6-5-2013).pdf | 2018-08-11 |
| 21 | 1145-MUM-2013-CLAIMS [26-07-2019(online)].pdf | 2019-07-26 |
| 22 | 1145-MUM-2013-Response to office action [12-04-2021(online)].pdf | 2021-04-12 |
| 22 | 1145-MUM-2013-FORM 3.pdf | 2018-08-11 |
| 23 | ABSTRACT1.jpg | 2018-08-11 |
| 23 | 1145-MUM-2013-US(14)-HearingNotice-(HearingDate-07-05-2021).pdf | 2021-10-03 |
| 1 | 1145_MUM_2013_search_08-01-2019.pdf |