The present disclosure relates to the field of marketing and, in particular, relates to method and system for creating high confidence micro-personas through hybrid machine learning methods.
BACKGROUND
[0002] Over the past few years, online platforms have become a popular way for individuals and consumers to interact online. The online platforms have been used to provide range of services to the individuals on the Internet. The range of services such as marketplaces, search engines, social media, consumer business, financial services, industrial products, home services, legal services, creative services, e-learning services, and the like. In addition, the online platforms facilitate interactions between at least two or more distinct individuals (whether firms or consumers) through the range of services via the Internet. There has been an increase in demand for these services and usage of the online platforms. The increasing demand of the online platforms leads to a competitive environment within online platform providers. In this competitive environment, the online platform providers are striving to continuously increase consumer engagement and stickiness by driving relevant campaigns. However, due to lack of personalization and understanding of the targeted individuals, the campaign returns are invariably poor. The problem lies in understanding the individuals and consumers, his/her persona and matching the right kind of offer, at the right time and in the right context in this dynamically changing data driven world.
[0003] The online platform providers are seeking effective ways to run the marketing campaigns. In addition, the online platform providers seek to have a high successful rate of the marketing campaigns. However, the present systems and methods for creating high confidence micro-personas are not based on hybrid machine learning algorithms.
[0004] In addition, the present systems and methods do not allow the online platform providers to generate accurate micro-personas for contextual engagement and hypertargeting. Further, the present systems and methods do not allow the

online platform providers to provide good customer experience through targeted marketing campaigns to the micro-personas. Furthermore, the present systems and methods do not allow the online platform providers to have a high return on investment for marketing campaigns.
[0005] In light of the above stated discussion, there is a need for efficient and effective system that overcomes the above stated disadvantages.
OBJECT OF THE DISCLOSURE
[0006] A primary object of the present disclosure is to generate accurate micro-personas for contextual engagement and hypertargeting.
[0007] Another object of the present disclosure is to provide a combination of unsupervised machine learning and supervised machine learning.
[0008] Yet another object of the present disclosure is to increase a confidence index of the micro-personas.
[0009] Yet another object of the present disclosure is to provide good customer experience through targeted marketing campaigns to the micro-personas.
[0010] Yet another object of the present disclosure is to provide high loyalty index through precise marketing campaigns driven by enriched customer knowledge.
SUMMARY
[0011] The present disclosure provides a computer system. The computer system includes one or more processors, a signal generator circuitry embedded inside a computing device for generating a signal, and a memory. The memory is coupled to the one or more processors. The memory stores instructions. The instructions are executed by the one or more processors. The execution of instructions causes the one or more processors to perform a method for creating high confidence micro-personas through hybrid machine learning methods. The method includes a first step to receive a plurality of data associated with a plurality of subscribers at a campaign management system. The plurality of subscribers is associated with one or more communication devices. The plurality of data is received in real-time. The method includes a second step to pre-process the plurality of data associated with the plurality of subscribers at the campaign

management system. The pre-processing is done for management of the plurality of data and initiating generation of a plurality of clusters. The plurality of data is pre-processed in real-time.
[0012] The method includes a third step to cluster the plurality of data for generation of the plurality of clusters based on one or more attributes at the campaign management system. The plurality of clusters is generated using one or more unsupervised machine learning algorithms. The clustering is performed recursively and in real-time.
[0013] The method includes a fourth step to dynamically create a plurality of micro-personas associated with the plurality of subscribers for each of the plurality of clusters generated using the one or more unsupervised machine learning algorithms at the campaign management system. In addition, each of the plurality of micro-personas is created to detail out the one or more attributes of the plurality of clusters for each of the plurality of subscribers. Further, the plurality of micro-personas is created to further split the plurality of clusters based on the one or more attributes. Furthermore, the plurality of micro-personas is created to hyper-personalize one or more marketing campaigns for each of the plurality of subscribers. Moreover, the plurality of micro-personas is dynamically created in real-time.
[0014] The method includes a fifth step to filter the plurality of micro-personas based on a probabilistic information of a click-through rate for each of the plurality of subscribers of the plurality of clusters at the campaign management system. The plurality of micro-personas is filtered using one or more supervised machine learning algorithms. The plurality of micro-personas is filtered in real¬time. In addition, the campaign management system enables planning, execution, tacking, and analysis of the one or more marketing campaigns. Further, the campaign management system runs the one or more marketing campaigns for the plurality of subscribers in a personalized and efficient manner. Furthermore, the campaign management system provides genuine understanding of requirement of each of the plurality of subscribers. Moreover, the campaign management system runs on a combination of the one or more unsupervised machine learning algorithms

and the one or more supervised machine learning algorithms. Also, the campaign management system increases a confidence index of the plurality of subscribers. Also, the confidence index is an indicator to measure degree of optimism of the plurality of subscribers. Also, the confidence index is computed based on the probabilistic information and the one or more attributes of the plurality of micro-personas. Also, the high confidence index leads to high click-through rate. Also, a micro-persona of the plurality of micro-personas is included for the one or more marketing campaigns when the confidence index reaches a pre-defined limit.
[0015] In an embodiment of the present disclosure, the plurality of data includes customer relationship management data, business support system data, data usage, and voice data. In another embodiment of the present disclosure, the plurality of data includes location data, roaming data, and social media data. In addition, customer relationship management data and business support system data are static dataset. Further, data usage, voice data, location data, roaming data, and social media data are dynamic dataset.
[0016] In an embodiment of the present disclosure, the pre-processing includes cleaning, and normalization of the plurality of data. In addition, the cleaning corresponds to filling missing values in the plurality of data and ignoring noise in the plurality of data. Further, the normalization is applied to change values of numeric columns in the plurality of data to a common scale without distorting differences in the ranges of values. Furthermore, the normalization reduces redundancy and dependency in the plurality of data.
[0017] In an embodiment of the present disclosure, the method further creates a machine learning model to cluster the plurality of data for generation of the plurality of clusters at the campaign management system. The machine learning model works on the one or more unsupervised machine learning algorithms and the one or more supervised machine learning algorithms. The machine learning model is a hybrid machine learning model.
[0018] In an embodiment of the present disclosure, the one or more attributes include age, gender, marital status, location, real-time subscriber location, date of birth, bill mode, and preferred language. In addition, the one or more

attributes further include salaried subscriber, business owner, subscriber plan name, plan price, maximum voice limit, maximum data limit, and maximum short message service limit. Further, the one or more attributes further include roaming details, actual voice used, actual data used, data speed, number of data sessions, actual short message service used, and actual roaming used. Furthermore, the one or more attributes further include value-added service, type of value-added service, price of value-added service, number of customer care service requests, subscriber payments, and mode of payment. Moreover, the one or more attributes further include dunning requests, credit amount, device internet protocol address, device model, device type, device operating system, and device brand.
[0019] In an embodiment of the present disclosure, the method further initiates the one or more marketing campaigns for the plurality of subscribers at the campaign management system. The one or more marketing campaigns are initiated based on the plurality of micro-personas. The one or more marketing campaigns are initiated in the real-time.
[0020] In an embodiment of the present disclosure, the method further displays one or more advertisements associated with the one or more marketing campaigns at the campaign management system. The one or more advertisements are displayed to each of the plurality of subscribers on the one or more communication devices based on the plurality of micro-personas. The one or more advertisements are displayed in the real-time on the one or more communication devices.
[0021] In an embodiment of the present disclosure, the method further obtains a response of each of the plurality of subscribers at the campaign management system. The response corresponds to reaction of each of the plurality of subscribers for each of the one or more advertisements. The response is sent to a campaign history database. The response in obtained in real-time.
[0022] In an embodiment of the present disclosure, the probabilistic information of the click-through rate is predicted for each of the one or more advertisements. The click-through rate for each of the one or more advertisements is predicted using the one or more supervised machine learning algorithms of the

machine learning model. In addition, the probabilistic information of the click-through rate of each of the plurality of subscribers is a simple average of probabilities of each of the plurality of micro-personas.
STATEMENT OF THE DISCLOSURE [0023] The present disclosure provides a computer system. The computer system includes one or more processors, a signal generator circuitry embedded inside a computing device for generating a signal, and a memory. The memory is coupled to the one or more processors. The memory stores instructions. The instructions are executed by the one or more processors. The execution of instructions causes the one or more processors to perform a method for creating high confidence micro-personas through hybrid machine learning methods. The method includes a first step to receive a plurality of data associated with a plurality of subscribers at a campaign management system. The plurality of subscribers is associated with one or more communication devices. The plurality of data is received in real-time. The method includes a second step to pre-process the plurality of data associated with the plurality of subscribers at the campaign management system. The pre-processing is done for management of the plurality of data and initiating generation of a plurality of clusters. The plurality of data is pre-processed in real-time. The method includes a third step to cluster the plurality of data for generation of the plurality of clusters based on one or more attributes at the campaign management system. The plurality of clusters is generated using one or more unsupervised machine learning algorithms. The clustering is performed recursively and in real-time. The method includes a fourth step to dynamically create a plurality of micro-personas associated with the plurality of subscribers for each of the plurality of clusters generated using the one or more unsupervised machine learning algorithms at the campaign management system. In addition, each of the plurality of micro-personas is created to detail out the one or more attributes of the plurality of clusters for each of the plurality of subscribers. Further, the plurality of micro-personas is created to further split the plurality of clusters based on the one or more attributes. Furthermore, the plurality of micro-personas is created to hyper-personalize one or more marketing campaigns for each of the

plurality of subscribers. Moreover, the plurality of micro-personas is dynamically created in real-time.. The method includes a fifth step to filter the plurality of micro-personas based on a probabilistic information of a click-through rate for each of the plurality of subscribers of the plurality of clusters at the campaign management system. The plurality of micro-personas is filtered using one or more supervised machine learning algorithms. The plurality of micro-personas is filtered in real¬time. In addition, the campaign management system enables planning, execution, tacking, and analysis of the one or more marketing campaigns. Further, the campaign management system runs the one or more marketing campaigns for the plurality of subscribers in a personalized and efficient manner.
[0024] Furthermore, the campaign management system provides genuine understanding of requirement of each of the plurality of subscribers. Moreover, the campaign management system runs on a combination of the one or more unsupervised machine learning algorithms and the one or more supervised machine learning algorithms. Also, the campaign management system increases a confidence index of the plurality of subscribers. Also, the confidence index is an indicator to measure degree of optimism of the plurality of subscribers. Also, the confidence index is computed based on the probabilistic information and the one or more attributes of the plurality of micro-personas. Also, the high confidence index leads to high click-through rate. Also, a micro-persona of the plurality of micro-personas is included for the one or more marketing campaigns when the confidence index reaches a pre-defined limit.
BRIEF DESCRIPTION OF FIGURES
[0025] Having thus described the disclosure in general terms, reference will now be made to the accompanying figures, wherein:
[0026] FIG. 1 illustrates an interactive computing environment for creating high confidence micro-personas through hybrid machine learning methods, in accordance with an embodiment of the present disclosure; and
[0027] FIG. 2 illustrates a block diagram of a computing device, in accordance with various embodiments of the present disclosure.

[0028] It should be noted that the accompanying figures are intended to present illustrations of exemplary embodiments of the present disclosure. These figures are not intended to limit the scope of the present disclosure. It should also be noted that accompanying figures are not necessarily drawn to scale.

DETAILED DESCRIPTION
[0029] Reference will now be made in detail to selected embodiments of the present disclosure in conjunction with accompanying figures. The embodiments described herein are not intended to limit the scope of the disclosure, and the present disclosure should not be construed as limited to the embodiments described. This disclosure may be embodied in different forms without departing from the scope and spirit of the disclosure. It should be understood that the accompanying figures are intended and provided to illustrate embodiments of the disclosure described below and are not necessarily drawn to scale. In the drawings, like numbers refer to like elements throughout, and thicknesses and dimensions of some components may be exaggerated for providing better clarity and ease of understanding.
[0030] It should be noted that the terms "first", "second", and the like, herein do not denote any order, ranking, quantity, or importance, but rather are used to distinguish one element from another. Further, the terms "a" and "an" herein do not denote a limitation of quantity, but rather denote the presence of at least one of the referenced item.
[0031] FIG. 1 illustrates an interactive computing environment 100 for creating high confidence micro-personas through hybrid machine learning methods, in accordance with an embodiment of the present disclosure. The interactive computing environment 100 includes a plurality of subscribers 102, one or more communication devices 104, and a communication network 106. In addition, the interactive computing environment 100 includes a campaign management system 108, a server 110, a database 114, and an administrator 112.
[0032] The interactive computing environment 100 includes the plurality of subscribers 102. In addition, the plurality of subscribers 102 may be any person or individual accessing the one or more communication devices 104. In an embodiment of the present disclosure, the plurality of subscribers 102 is owner of the one or more communication devices 104. In another embodiment of the present disclosure, the plurality of subscribers 102 is not the owner of the one or more communication devices 104. In an embodiment of the present disclosure, the plurality of subscribers 102 accesses the one or more communication devices 104

at home. In another embodiment of the present disclosure, the plurality of subscribers 102 accesses the one or more communication devices 104 at a cafe. In yet another embodiment of the present disclosure, the plurality of subscribers 102 accesses the one or more communication devices 104 at office. In an example, a subscriber SI accesses a communication device Dl (let's say a smartphone) while sitting in a living room. In another example, a subscriber S2 accesses a communication device D2 (let's say a laptop) while travelling from one place to another. In yet another example, a subscriber S3 accesses a communication device D3 (let's say a desktop computer) while working at office.
[0033] The interactive computing environment 100 is any environment which facilitates interaction of the plurality of subscribers 102 with one or more online platforms. In general, online platforms are computing platforms which enable various individuals to obtain, upload and access valuable resources or services. In addition, the one or more platforms include a plurality of contents. In an embodiment of the present disclosure, the plurality of contents includes but may not be limited to a plurality of OTT media contents, a plurality of products, a plurality of financial services, and one or more social media contents. In another embodiment of the present disclosure, the plurality of contents includes but may not be limited to a plurality of health services, a plurality of educational services, a plurality of real estate services, and a plurality of travel services. However, the plurality of contents is not limited to the above-mentioned contents.
[0034] In an embodiment of the present disclosure, the one or more online platforms correspond to android operating system compatible application. In another embodiment of the present disclosure, the one or more online platforms correspond to windows operating system compatible applications. In yet another embodiment of the present disclosure, the one or more online platforms correspond to iPhone operating system compatible applications. In yet another embodiment of the present disclosure, the one or more online platforms correspond to mac operating system compatible applications. In yet another embodiment of the present disclosure, the one or more online platforms correspond to webpages.

However, the one or more online platforms are not limited to the above-mentioned online platforms.
[0035] The interactive computing environment 100 includes the one or more communication devices 104. The plurality of subscribers 102 is connected with the interactive computing environment 100 through the one or more communication devices 104. In an embodiment of the present disclosure, the one or more communication devices 104 facilitate access to the one or more online platforms. In an embodiment of the present disclosure, each of the one or more communication devices 104 is a portable communication device. The portable communication device includes but may not be limited to a laptop, smartphone, tablet, and smart watch. In an example, the smartphone may be an iOS-based smartphone, an android-based smartphone, a windows-based smartphone and the like. In another embodiment of the present disclosure, each of the one or more communication devices 104 is a fixed communication device. The fixed communication device includes but may not be limited to desktop, workstation, smart TV and mainframe computer. In an embodiment of the present disclosure, the one or more communication devices 104 are currently in the switched-on state. The one or more communication devices 104 are any type of devices having an active internet. In addition, each of the plurality of subscribers 102 accesses corresponding communication device of the one or more communication devices 104 in real-time.
[0036] In an embodiment of the present disclosure, the one or more communication devices 104 perform computing operations based on a suitable operating system installed inside the one or more communication devices 104. In general, the operating system is system software that manages computer hardware and software resources and provide common services for computer programs. In addition, the operating system acts as an interface for software installed inside the one or more communication devices 104 to interact with hardware components of the one or more communication devices 104. In an embodiment of the present disclosure, each of the one or more communication devices 104 perform computing operations based on any suitable operating system designed for the portable

communication device. In an example, the operating system installed inside the one or more communication devices 104 is a mobile operating system. Further, the mobile operating system includes but may not be limited to windows operating system, android operating system, iOS operating system, Symbian operating system, BADA operating system from and BlackBerry operating system, and Sailfish. However, the operating system is not limited to above mentioned operating systems. In an embodiment of the present disclosure, the one or more communication devices 104 operate on any version of particular operating system corresponding to above mentioned operating systems.
[0037] In another embodiment of the present disclosure, the one or more communication devices 104 perform computing operations based on any suitable operating system designed for fixed communication device. In an example, the operating system installed inside the one or more communication devices 104 is windows. In another example, the operating system installed inside the one or more communication devices 104 is Mac. In yet another example, the operating system installed inside the one or more communication devices 104 is Linux based operating system. In yet another example, the operating system installed inside the one or more communication devices 104 is Chrome OS. In yet another example, the operating system installed inside the one or more communication devices 104 may be one of UNIX, Kali Linux, and the like. However, the operating system is not limited to above mentioned operating systems.
[0038] In an embodiment of the present disclosure, the one or more communication devices 104 operate on any version of windows operating system. In another embodiment of the present disclosure, the one or more communication devices 104 operate on any version of Mac operating system. In yet another embodiment of the present disclosure, the one or more communication devices 104 operate on any version of Linux operating system. In yet another embodiment of the present disclosure, the one or more communication devices 104 operates on any version of Chrome OS. In yet another embodiment of the present disclosure, the one or more communication devices 104 operates on any version of particular operating system corresponding to above mentioned operating systems.

[0039] In an embodiment of the present disclosure, the one or more online platforms are installed on the one or more communication devices 104. The one or more online platforms allow the plurality of subscribers 102 to access the plurality of contents. In another embodiment of the present disclosure, the one or more online platforms are hosted and accessed on a plurality of web browsers installed on the one or more communication devices 104. In an example, the plurality of web browsers includes but may not be limited to Opera, Mozilla Firefox, Google Chrome, Internet Explorer, Microsoft Edge, Safari and UC Browser. Further, the plurality of web browsers installed on the one or more communication devices 104 runs on any version of the respective web browser of the above mentioned web browsers. In an example, a subscriber SI opens an e-commerce application El to buy cutlery items. In another example, a subscriber S2 accesses a fintech wepage F2 on Google Chrome for a car loan.
[0040] The one or more communication devices 104 is connected to the communication network 106. The communication network 106 provides medium to the one or more communications devices 104 to connect to the campaign management system 108. Also, the communication network 106 provides network connectivity to the one or more communication devices 104. In an example, the communication network 106 uses protocol to connect the one or more communication devices 104 to the campaign management system 108. The communication network 106 connects the one or more communication devices 104 to the campaign management system 108 using a plurality of methods. The plurality of methods used to provide network connectivity to the one or more communication devices 104 includes 2G, 3G, 4G, Wifi and the like.
[0041] In an embodiment of the present disclosure, the communication network 106 may be any type of network that provides internet connectivity to the one or more communication devices 104. In an embodiment of the present disclosure, the communication network 106 is a wireless mobile network. In another embodiment of the present disclosure, the communication network 106 is a wired network with a finite bandwidth. In yet another embodiment of the present disclosure, the communication network 106 is combination of the wireless and the

wired network for optimum throughput of data transmission. In yet another embodiment of the present disclosure, the communication network 106 is an optical fiber high bandwidth network that enables high data rate with negligible connection drops.
[0042] In addition, the one or more communication devices 104 embed a signal generator circuitry. The one or more communication devices 104 embed the signal generator circuitry to trigger a signal for communicating information between the associated systems in real time. In an embodiment of the present disclosure, the signal generator circuitry generates a signal to trigger one or more hardware components associated with the one or more communication devices 104. The one or more hardware components are triggered for one or more purposes. The one or more purposes include but are not limited to receive a plurality of data, pre-process the plurality of data, cluster the plurality of data, predict probability of a click-through rate, and the like. The one or more purposes include generating signal based on requirement of the campaign management system 108.
[0043] The interactive computing environment 100 includes the campaign management system 108. In addition, the campaign management system 108 enables planning, execution, tacking, and analysis of one or more marketing campaigns. Further, the campaign management system 108 runs the one or more marketing campaigns for the plurality of subscribers 102 in a personalized and efficient manner. Furthermore, the campaign management system 108 provides genuine understanding of requirement of each of the plurality of subscribers 102. Moreover, the campaign management system 108 runs on a combination of one or more unsupervised machine learning algorithms and one or more supervised machine learning algorithms. Also, the campaign management system 108 increases a confidence index of the plurality of subscribers 102. Also, the confidence index is an indicator to measure degree of optimism of the plurality of subscribers 102. Also, the confidence index is computed based on a probabilistic information and one or more attributes of a plurality of micro-personas. Also, the high confidence index leads to high click-through rate.

[0044] The campaign management system 108 receives the plurality of data associated with the plurality of subscribers 102. The plurality of data is received in real-time. The plurality of data includes customer relationship management data, business support system data, data usage, voice data, location data, roaming data, and social media data. The customer relationship management data and business support system data are static dataset. In general, a customer relationship management database encompasses all the customer data that is collected, stored and analyzed using customer relationship management program. The data usage, voice data, location data, roaming data, and social media data are dynamic dataset. In general, location data has information that a communication device provides about current position in space. In general, social media data refers to each of the raw insights and information collected from person's social media activity.
[0045] The campaign management system 108 pre-processes the plurality of data associated with the plurality of subscribers 102. The pre-processing is done for management of the plurality of data and initiating generation of a plurality of clusters. The plurality of data is pre-processed in real-time. The pre-processing includes aggregation and collation of each of the plurality of data associated with the plurality of subscribers 102. In general, data aggregation is one sort of data and information mining process where data is searched, gathered and presented in summarized format. In general, collation is the assembly of data into a standard order. In addition, collation is based on numerical order or alphabetical order or extensions and combinations thereof. The pre-processing includes cleaning, and normalization of the plurality of data. In addition, the cleaning corresponds to filling missing values in the plurality of data and ignoring noise in the plurality of data. In an embodiment of the present disclosure, the missing values in the plurality of data are filled manually. In another embodiment of the present disclosure, the missing values in the plurality of data are filled using attribute mean. In yet another embodiment of the present disclosure, the missing values in the plurality of data are filled using probable value. Further, the normalization is applied to change values of numeric columns in the plurality of data to a common scale without distorting differences in the ranges of values. Furthermore, the normalization reduces

redundancy and dependency in the plurality of data. In general, data normalization is the process of structuring a relational database in accordance with a series of normal forms in order to reduce data redundancy and improve data integrity.
[0046] The campaign management system 108 clusters the plurality of data for generation of the plurality of clusters based on the one or more attributes. The one or more attributes include age, gender, marital status, location, real-time subscriber location, date of birth, bill mode, and preferred language. In addition, the one or more attributes further include salaried subscriber, business owner, subscriber plan name, plan price, maximum voice limit, maximum data limit, and maximum short message service limit. Further, the one or more attributes further include roaming details, actual voice used, actual data used, data speed, number of data sessions, actual short message service used, and actual roaming used. Furthermore, the one or more attributes further include value-added service, type of value-added service, price of value-added service, number of customer care service requests, subscriber payments, and mode of payment. Also, the one or more attributes further include dunning requests, credit amount, device internet protocol address, device model, device type, device operating system, and device brand. The plurality of clusters is generated using the one or more unsupervised machine learning algorithms. The clustering is performed recursively and in real-time. In an embodiment of the present disclosure, the plurality of clusters is defined as a plurality of personas. In general, personas are raw subscriber profiles. In an embodiment of the present disclosure, the one or more unsupervised machine learning algorithms include k-means and hierarchical clustering. In another embodiment of the present, the one or more unsupervised machine learning algorithms include mixture models, density-based spatial clustering of applications with noise, and OPTICS algorithm. However, the one or more unsupervised machine learning algorithms are not limited to the above-mentioned algorithms. The one or more unsupervised machine learning algorithms are applied recursively until maximum inter-cluster distance of the plurality of clusters is achieved. The one or more unsupervised machine learning algorithms are applied recursively until minimum intra-cluster distance of the plurality of clusters is achieved. The one or

more unsupervised machine leaning algorithms are run for achieving an optimum threshold of the plurality of micro-personas. The one or more unsupervised machine learning algorithms depends on performance of one or more supervised machine learning algorithms in past. In addition, the campaign management system 108 creates a machine learning model to cluster the plurality of data for generation of the plurality of clusters. The machine learning model works on the one or more unsupervised machine learning algorithms and the one or more supervised machine learning algorithms. In an embodiment of the present disclosure, the machine learning model is a hybrid machine learning model.
[0047] The campaign management system 108 dynamically creates the plurality of micro-personas associated with the plurality of subscribers for each of the plurality of clusters generated using the one or more unsupervised machine learning algorithms. In addition, each of the plurality of micro-personas is created to detail out the one or more attributes of the plurality of clusters for each of the plurality of subscribers 102. Further, the plurality of micro-personas is created to further split the plurality of clusters based on the one or more attributes. Furthermore, the plurality of micro-personas is created to hyper-personalize the one or more marketing campaigns for the plurality of subscribers 102. Also, the plurality of micro-personas is dynamically created in real-time. Also, a micro-persona of the plurality of micro-personas is included for the one or more marketing campaigns when the confidence index reaches a pre-defined limit. In an embodiment of the present disclosure, the micro-persona is included in the one or more marketing campaigns when the confidence index reaches 5. In another embodiment of the present disclosure, the micro-persona is included in the one or more marketing campaigns when the confidence index reaches 2. In yet another embodiment of the present disclosure, the micro-persona is included in the one or more marketing campaigns when the confidence index reaches 3.
[0048] The campaign management system 108 initiates the one or more marketing campaigns for the plurality of subscribers 102 to achieve one or more goals. In general, goal refers to any target for any event for a specific subscriber in a selected timeframe. In addition, the one or more marketing campaigns are

initiated based on the plurality of micro-personas by a plurality of advertisers. The one or more marketing campaigns are initiated in the real-time. Further, the plurality of advertisers purchases one or more advertisement slots from the one or more online platforms. In an embodiment of the present disclosure, the plurality of advertisers purchases the one or more advertisement slots for displaying one or more advertisements on the corresponding advertisement slots.
[0049] In general, the one or more marketing campaigns are organized, strategized efforts for marketing to the plurality of subscribers 102. The one or more marketing campaigns reach the plurality of subscribers 102 over a plurality of channels. The plurality of channels include but may not be limited to mobile channels, email channels, desktop channels, social channels, remarketing channels, server channels, and the like. However, the various channels are not limited to the above-mentioned channels. The one or more marketing campaigns may include advertiser defined parameters. The advertiser defined parameters include minimum spend, discounts, campaign duration, campaign relevancy, campaign location, a customer's patronage of the online platform, subscriber interaction, and the like. However, the advertiser defined parameters are not limited to the above-mentioned parameters.
[0050] The campaign management system 108 displays the one or more advertisements to the plurality of subscribers 102 on corresponding advertisement slot of the one or more advertisement slots. The one or more advertisements are associated with the one or more marketing campaigns. In an embodiment of the present disclosure, the one or more advertisements are displayed on the one or more communication devices 104 in the form of flash messages. In another embodiment of the present disclosure, the one or more advertisements are displayed on the one or more communication devices 104 in the form of text messages. In yet another embodiment of the present disclosure, the one or more advertisements are displayed on the one or more communication devices 104 in the form of telephonic calls. In yet another embodiment of the present disclosure, the one or more advertisements are displayed on the one or more communication devices 104 in the form of multimedia messages. In yet another embodiment of the present disclosure, the one

or more advertisements are displayed on the one or more online platforms in the form of notification. In yet another embodiment of the present disclosure, the one or more advertisements are displayed on the one or more communication devices 104 as Google Ads. The one or more advertisements are displayed on the one or more communication devices 104 in real-time. In an embodiment of the present disclosure, the one or more advertisements displayed are associated with the interests of the plurality of subscribers 102. In addition, the one or more advertisements include text advertisements, video advertisements, audio advertisements, audio-video advertisements, pictorial advertisements, and the like.
[0051] The campaign management system 108 obtains a response of each of the plurality of subscribers 102. The response in obtained in real-time. The response corresponds to reaction of each of the plurality of subscribers 102 corresponding to the one or more advertisements viewed by the plurality of subscribers 102. The response is sent to a campaign history database. In general, the campaign history database stores information associated with response of subscribers for advertisements related to past marketing campaigns.
[0052] The campaign management system 108 filters the plurality of micro-personas based on a probabilistic information of a click-through rate for each of the plurality of subscribers 102 of the plurality of clusters. The plurality of micro-personas is filtered using the one or more supervised machine learning algorithms. The plurality of micro-personas is filtered in real-time. In an embodiment of the present disclosure, the one or more supervised machine learning algorithms include gradient boosted decision trees and one-class support vector machine. In another embodiment of the present disclosure, the one or more supervised machine learning algorithms include linear regression, logistic regression, and k-nearest neighbor algorithm. However, the one or more supervised machine learning algorithms are not limited to the above-mentioned algorithms. In addition, the probabilistic information of the click-through rate is predicted for each of the one or more advertisements. The click-through rate for each of the one or more advertisements is predicted using the one or more supervised machine learning algorithms of the machine learning model. In addition, the probabilistic information of the click-

through rate of each of the plurality of subscribers 102 is a simple average of probabilities of each of the plurality of micro-personas.
[0053] Furthermore, the interactive computing environment 100 includes the server 110 and the database 114. The campaign management system 108 is associated with the server 110. In general, server is a computer program or device that provides functionality for other programs or devices. In addition, server provides various functionalities, such as sharing data or resources among multiple subscribers, or performing computation for the subscriber. However, those skilled in the art would appreciate that the campaign management system 108 is connected to more number of servers. Furthermore, it may be noted that the server 110 includes the database 114. However, those skilled in the art would appreciate that more number of the servers include more numbers of database.
[0054] In an embodiment of the present disclosure, the campaign management system 108 is installed in the server 110. In another embodiment of the present disclosure, the campaign management system 108 is connected with the server 110. In yet another embodiment of the present disclosure, the campaign management system 108 is a part of the server 110. The server 110 handles each operation and task performed by the campaign management system 108. The server 110 stores one or more instructions for performing the various operations of the campaign management system 108. The server 110 is located remotely. The server 110 is associated with the administrator 112. In general, administrator manages the different components in the campaign management system. The administrator 112 coordinates the activities of the components involved in the campaign management 108. The administrator 112 is any person or individual who monitors the working of the campaign management system 108 and the server 110 in real time. The administrator 112 monitors the working of the campaign management system 108 and the server 110 through a communication device. The communication device includes the laptop, the desktop computer, the tablet, a personal digital assistant and the like.
[0055] The database 114 stores different sets of information associated with various components of the campaign management system 108. The database 114

is used to store general information and specialized data, such as characteristics data of the plurality of subscribers 102, data of the one or more communication devices 104, and the like. The database 114 stores information of the plurality of subscribers 102, the one or more communication devices 104, the plurality of data, and the like. The database 114 organizes the data using model such as relational models or hierarchical models. Further, the database 114 stores data provided by the plurality of subscribers 102 and the administrator 112.
[0056] FIG. 2 illustrates the block diagram of a computing device 200, in accordance with various embodiments of the present disclosure. The computing device 200 includes a bus 202 that directly or indirectly couples the following devices: memory 204, one or more processors 206, one or more presentation components 208, one or more input/output (I/O) ports 210, one or more input/output components 212, and an illustrative power supply 214. The bus 202 represents what may be one or more busses (such as an address bus, data bus, or combination thereof). Although the various blocks of FIG. 2 are shown with lines for the sake of clarity, in reality, delineating various components is not so clear, and metaphorically, the lines would more accurately be grey and fuzzy. For example, one may consider a presentation component such as a display device to be an I/O component. Also, processors have memory. The inventors recognize that such is the nature of the art, and reiterate that the diagram of FIG. 2 is merely illustrative of an exemplary computing device 200 that can be used in connection with one or more embodiments of the present invention. Distinction is not made between such categories as "workstation," "server," "laptop," "hand-held device," etc., as all are contemplated within the scope of FIG. 2 and reference to "computing device."
[0057] The computing device 200 typically includes a variety of computer-readable media. The computer-readable media can be any available media that can be accessed by the computing device 200 and includes both volatile and nonvolatile media, removable and non-removable media. By way of example, and not limitation, the computer-readable media may comprise computer storage media and communication media. The computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or

technology for storage of information such as computer-readable instructions, data structures, program modules or other data.
[0058] The computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by the computing device 200. The communication media typically embodies computer-readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared and other wireless media. Combinations of any of the above should also be included within the scope of computer-readable media.
[0059] Memory 204 includes computer-storage media in the form of volatile and/or nonvolatile memory. The memory 204 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard drives, optical-disc drives, etc. The computing device 200 includes one or more processors that read data from various entities such as memory 204 or I/O components 212. The one or more presentation components 208 present data indications to a subscriber or other device. Exemplary presentation components include a display device, speaker, printing component, vibrating component, etc. The one or more I/O ports 210 allow the computing device 200 to be logically coupled to other devices including the one or more I/O components 212, some of which may be built in. Illustrative components include a microphone, joystick, game pad, satellite dish, scanner, printer, wireless device, etc.
[0060] The present disclosure has numerous advantages over the prior art. The present disclosure provides a campaign management system to generate

accurate micro-personas for contextual engagement and hypertargeting. The present disclosure provides the campaign management system that runs on a combination of unsupervised machine learning and supervised machine learning applied recursively. The present disclosure provides the campaign management system to increase confidence index of the micro-personas. The present disclosure provides the campaign management system to offer good customer experience through targeted marketing campaigns to the micro-personas. The present disclosure provides the campaign management system to offer high loyalty index through precise marketing campaigns driven by enriched subscriber knowledge.
[0061] The foregoing descriptions of pre-defined embodiments of the present technology have been presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the present technology to the precise forms disclosed, and obviously many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the present technology and its practical application, to thereby enable others skilled in the art to best utilize the present technology and various embodiments with various modifications as are suited to the particular use contemplated. It is understood that various omissions and substitutions of equivalents are contemplated as circumstance may suggest or render expedient, but such are intended to cover the application or implementation without departing from the spirit or scope of the claims of the present technology.

We claim:

1. A computer system comprising:
one or more processors (206); and
a memory (204) coupled to the one or more processors (206), the memory (204) for storing instructions which, when executed by the one or more processors (206) , cause the one or more processors (206) to perform a method for creating high confidence micro-persona through hybrid machine learning methods, the method comprising:
receiving, at a campaign management system (108), a plurality of data associated with a plurality of subscribers (102), wherein the plurality of data is received in real-time;
pre-processing, at the campaign management system (108), the plurality of data associated with the plurality of subscribers (102), wherein the pre-processing is done for management of the plurality of data and initiating generation of a plurality of clusters, wherein the plurality of data is pre-processed in real-time;
clustering, at the campaign management system (108), the plurality of data for generation of the plurality of clusters based on one or more attributes, wherein the plurality of clusters is generated using one or more unsupervised machine learning algorithms, wherein the clustering is performed recursively and in real-time;
dynamically creating, at the campaign management system (108), a plurality of micro-personas associated with the plurality of subscribers (102) for each of the plurality of clusters generated using the one or more unsupervised machine learning algorithms, wherein each of the plurality of micro-personas is created to detail out the one or more attributes of the plurality of clusters for each of the plurality of subscribers (102), wherein the plurality of micro-personas is created to further split the plurality of

clusters based on the one or more attributes, the plurality of micro-personas is created to hyper-personalize one or more marketing campaigns for the plurality of subscribers (102), wherein the plurality of micro-personas is dynamically created in real-time; and
filtering, at the campaign management system (108), the plurality of micro-personas based on a probabilistic information of a click-through rate for each of the plurality of subscribers (102) of the plurality of clusters, wherein the plurality of micro-personas is filtered using one or more supervised machine learning algorithms, wherein the plurality of micro-personas is filtered in real-time,
wherein the campaign management system (108) enables planning, execution, tacking, and analysis of the one or more marketing campaigns, wherein the campaign management system (108) runs the one or more marketing campaigns for the plurality of subscribers (102) in a personalized and efficient manner, wherein the campaign management system (108) provides genuine understanding of requirement of each of the plurality of subscribers (102), wherein the campaign management system (108) runs on a combination of the one or more unsupervised machine learning algorithms and the one or more supervised machine learning algorithms, wherein the campaign management system (108) increases a confidence index of the plurality of subscribers (102), wherein the confidence index is an indicator to measure degree of optimism of the plurality of subscribers (102), wherein the confidence index is computed based on the probabilistic information and the one or more attributes of the plurality of micro-personas, wherein the high confidence index leads to high click-through rate, wherein a micro-persona of the plurality of micro-personas is included for the one or more marketing campaigns when the confidence index reaches a pre-defined limit.
2. The computer system as claimed in claim 1, wherein the plurality of data comprises customer relationship management data, business support system

data, data usage, voice data, location data, roaming data, and social media data, wherein the customer relationship management data and business support system data are static dataset, wherein data usage, voice data, location data, roaming data, and social media data are dynamic dataset.
The computer system as claimed in claim 1, wherein the pre-processing comprises cleaning, and normalization of the plurality of data, wherein the cleaning corresponds to filling missing values in the plurality of data and ignoring noise in the plurality of data, wherein the normalization is applied to change values of numeric columns in the plurality of data to a common scale without distorting differences in the ranges of values, wherein the normalization reduces redundancy and dependency in the plurality of data.
The computer system as claimed in claim 1, further comprising creating, at the campaign management system (108), a machine learning model to cluster the plurality of data for generation of the plurality of clusters, wherein the machine learning model works on the one or more unsupervised machine learning algorithms and the one or more supervised machine learning algorithms, wherein the machine learning model is a hybrid machine learning model.
The computer system as claimed in claim 1, wherein the one or more attributes comprise age, gender, marital status, location, real-time subscriber location, date of birth, bill mode, and preferred language, wherein the one or more attributes further comprise salaried subscriber, business owner, subscriber plan name, plan price, maximum voice limit, maximum data limit, and maximum short message service limit, wherein the one or more attributes further comprise roaming details, actual voice used, actual data used, data speed, number of data sessions, actual short message service used, and actual roaming used, wherein the one or more attributes further comprise value-added service, type of value-added service, price of value-added service, number of customer care service requests, subscriber payments, and mode of payment, wherein the one or more

attributes further comprise dunning requests, credit amount, device internet protocol address, device model, device type, device operating system, and device brand.
The computer system as claimed in claim 1, further comprising initiating, at the campaign management system (108), the one or more marketing campaigns for the plurality of subscribers (102), wherein the one or more marketing campaigns are initiated based on the plurality of micro-personas, wherein the one or more marketing campaigns are initiated in the real-time.
The computer system as claimed in claim 1, further comprising displaying, at the campaign management system (108), one or more advertisements associated with the one or more marketing campaigns for the plurality of micro-personas, wherein the one or more advertisements are displayed to each of the plurality of subscribers (102) on one or more communication devices (104) based on the plurality of micro-personas, wherein the one or more advertisements are displayed in the real-time on the one or more communication devices (104).
The computer system as claimed in claim 1, further comprising obtaining, at the campaign management system (108), a response of each of the plurality of subscribers (102), wherein the response corresponds to reaction of each of the plurality of subscribers (102) for each of the one or more advertisements, wherein the response is sent to a campaign history database, wherein the response in obtained in real-time.
The computer system as claimed in claim 1, wherein the probabilistic information of the click-through rate is predicted for each of the one or more advertisements, wherein the click-through rate for each of the one or more advertisements is predicted using the one or more supervised machine learning algorithms of the machine learning model, wherein the probabilistic

information of the click-through rate of each of the plurality of subscribers (102) is a simple average of probabilities of each of the plurality of micro-personas.