TECHNICAL FIELD
The present subject matter relates to the field of compatibility analysis, and more particularly to a method and system for determining compatible contenders for a contest.

BACKGROUND
Online gaming is becoming more and more popular as a means of socializing and online entertainment. Many of the popular online games/contests are multi-player and can also be Real Money Games (RMG) like Chess, Carrom, Poker, and many more. When a contender arrives on
an online gaming platform, it's very important to identify suitable partner(s) for them to participate. Matching of partners in an online game is very critical for the participants experience due to multiple reasons. For example, whether a person wins or loses the game is dependent on their skills as well as the skills of the partner they are paired with. For example, different contenders have different skills (e.g. fast moves vs. slow moves) and pairing with an appropriate partner is important
for a delightful gaming experience. Further, another important factor is to retain and keep the
participants engaged on the platform. It is evident that how people are matched in an online game
has a direct impact on the business metrics as well. Due to all of the above (non-exhaustive) reasons,
matching of players is an extremely important problem for online gaming platforms.
However, the technical challenge for retaining the participants and keeping them engaged is how analyze huge amount of data associated with the participants. Once the participants register with the gaming platforms, they play their natural game based on their skills and capability. While playing the huge data is generated which captures the participant's style of playing the game. However, the challenge is to understand the data of different players considering different
parameters.
The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known ) to a person skilled in the art.

SUMMARY
In one non-limiting example, a method of determining compatible contenders for a contest is disclosed. The method comprises detecting a set of contenders, from a plurality of contenders that are willing to participate in the contest at an instance, the method further comprising determining
a plurality of contender vectors corresponding to each contender of the set of contenders. The
plurality of contender vectors comprises at least one of a skill vector, a style vector and a profile
vector. Further, the method comprises applying a pretrained compatibility model upon the plurality
of contender vectors to determine a plurality of compatibility scores for each contender. The
plurality of compatibility scores determined for each contender indicates compatibility level of
each contender with other contenders of the set of contenders. The method further comprises identifying at least a pair of contenders, amongst the set of contenders, based on the plurality of compatibility scores determined for each contender of the set of contenders. The at least a pair of contenders indicates those contenders having highest level of matching for the contest amongst the set of contenders. Further, the compatibility model further learns about the compatibility of the set
of contenders based on the identifying, thereby updating the compatibility model with the
compatibility of the set of contenders.
In another embodiment, a system for determining compatible contenders for a contest comprises a detecting unit to detect a set of contenders, from the plurality of contenders that are willing to ) participate in the contest at an instance. The system further comprises a determining unit to determine a plurality of contender vectors corresponding to each contender of the set of contenders. The plurality of contender vectors comprises at least one of a skill vector, a style vector and a profile vector. Further the system comprises applying unit to apply a pretrained compatibility model upon the plurality of contender vectors to determine a plurality of compatibility scores for each
contender. The plurality of compatibility scores determined for each contender indicates
compatibility level of each contender with other contenders of the set of contenders. The system
further comprises identify at least a pair of contenders, amongst the set of contenders, based on the
plurality of compatibility scores determined for each contender of the set of contenders. The at least
a pair of contenders indicates those contenders having highest level of matching for the contest
amongst the set of contenders. Further, the compatibility model further learns about the

compatibility of the set of contenders based on the identifying, thereby updating the compatibility model with the compatibility of the set of contenders.
The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition > to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.
OBJECTS OF THE INVENTION:
The object of the present disclosure is to determine compatible contenders in such a manner to
enhance the experience of participation.
Another object of the present disclosure is to retain the engage the contenders while participating
in the contest. i
BRIEF DESCRIPTION OF THE DRAWINGS
The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed
embodiments. 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 figures to reference like features and components. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and with reference to the accompanying figures, in which:

Figure 1 describes an exemplary environment 100 for determining compatible contenders for a contest in accordance with an embodiment of the present invention.
Figure 2 describes a block diagram of system for determining compatible contenders for a contest in accordance with an embodiment of the present invention.

Figure 3 illustrates a flowchart describing a method of determining compatible contenders for the contest, in accordance with an embodiment of the present invention.
It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual
views of illustrative systems embodying the principles of the present subject matter. Similarly, it will
be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the
like represent various processes which may be substantially represented in computer readable
medium and executed by a computer or processor, whether or not such computer or processor is
explicitly shown.
DETAILED DESCRIPTION
In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described
herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other
embodiments.
In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration ) specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.
Disclosed herein is a method and system for determining compatible contenders to participate in
the contest. According to embodiments of present disclosure, the system analyzes the contenders
while they participate in the contest. The analysis is performed to understand how the contenders
participates in the contest. Some of the contenders may be new to the contest and some may be
regular. Depending upon their experience and style, different data may be generated, which the
system captures over the time. The system uses the data to model the participants in different

categories. Once the model is trained, the system applies the model in real-time scenario with an objective of identifying a suitable or best match pair of contenders for participating in the contest.
According to an embodiment, the present disclosure may implement a two-step approach to i enhance the experience of participation for the contenders while satisfying the preset contest paraments. The first step may comprise matching all the contenders based on preset parameters like retention time and engagement level and generating a contender matrix for determining a preliminary level matching between the contenders. Based on the contender matrix, a compatibility model is generated. Whereas, in the second step, system considers different data like skill data, ) style data and profile data of the contenders in a real-time. Using the skill data, style data and profile data, the system generates the contender vectors. Further, the system applies the pretrained compatibility model on the contender vectors to obtain compatibility scores that enable identifying at least a pair of contenders with highest level of matching for participating the contest.
The present disclosure addresses the shortcomings of the conventional art and proposes a method
and an apparatus for providing personalized navigational guidance to the user in the virtual world.
The term virtual world, virtual environment and virtual reality may be used to interchangeably
without departing from the scope of the present application.
Figure 1 describes an exemplary environment 100 for determining compatible contenders for a contest in accordance with an embodiment of the present invention. The environment 100 comprises a system 101, a communication network 105 and a plurality of contender devices 106-1, 106-2 ...106-n (collectively referred as 106) to enable a plurality of contenders (107-1, 107-2... 107-n (collectively referred as 107) connected with the communication network 105. Although, only three
contender devices and three contenders are shown in figure 1, the number of contender devices 106
and contenders 107 there can be more than three. Although the present disclosure is explained
considering that the system 101 is implemented on a server, it may be understood that the system 101
may 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, a cloud- based computing environment.

Further, the contender device 106 may comprise different types of computing device such as a mobile device, a smart phone, a tablet, a laptop, personal computer (PC) etc. Each of the contender devices are enabled with configuration to connect to the communication network 105 and have a display and I/O interfaces for the contenders to interact with a contest access platform.
In one implementation, the communication network 105 may be a wireless network, a wired network or a combination thereof. The communication network 105 may 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 communication network 105 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), Hypertext Transfer Protocol Secure (HTTPS), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like, to communicate with one another. Further the communication network 105 may include a variety of network devices, including routers, bridges,
servers, computing devices, storage devices, and the like.
Figure 1 is explained in conjunction with figure 2. In one implementation, the system 101 may comprise an I/O interface 104, a processor 102, a memory 103 and the units 211. The memory 103 may be communicatively coupled to the processor 102 and the units 211. Further, the memory 103 ) may store data 202 comprising contest optimisation parameters 203, contender matrix 204, contender data 205, compatibility model 206, contender vectors 207, compatibility scores 208, and other data 209. In some embodiments, the data may be stored in the memory in form of various data structures. Additionally, the data can be organized using data models, such as relational or hierarchical data models. The other data may store data, including temporary data and temporary
files, generated by the units 211 for performing the various functions of the system 101. As an
example, the other data may include data associated with the contender device requests to access
the server, regular contender devices 106 details corresponding to a contender 107, compatible
contender details upon determining etc.. .The significance and use of data 202 is explained in the
upcoming paragraphs of the specification. The processor 102 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 processor 102 is configured to fetch and execute computer-readable instructions stored in the memory 103. The I/O interface 104 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The I/O interface 104 may allow the system 101 to interact with the
user directly or through the user/contender devices 106. Further, the I/O interface 104 may enable
the system 101 to communicate with other computing devices, such as web servers and external
data servers (not shown). The I/O interface 104 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 104 may include
one or more ports for connecting many devices to one another or to another server.
In one implementation, the units 211 may comprise detecting unit 212, determining unit 213, applying unit 214 and identifying unit 215. According to embodiments of present disclosure, these units 212-215 may comprise hardware components like processor, microprocessor,
microcontrollers, application-specific integrated circuit for performing various operations of the
system 101. It must be understood to a person skilled in art that the processor 102 may perform all
the functions of the units 212-215 according to various embodiments of the present disclosure.
Now referring back to figure 1 showing the environment 100 in which the contenders 107 are ) connected to the through the contender devices 106. Initially, the contenders 107 registers on contest access platform (not shown in figure) for participating in the contest by providing their demographic details. It may be understood to a skilled person that the contest access platform may be any external server/platform, connected with the system 101 and the contender devices 106, which are capable of hosting the contest for the contenders 107. However, according to other
embodiments, the contest access platform may be installed within the system 101. Once the
registration is completed, the contenders 107 may choose different types of contest hosted on the
contest access platform and participate with other contenders 107 using their devices 106.
Since the objective of the present disclosure is to identify the compatible contenders 107 for
participating in the contest and keep them engaged, it is important to understand the behavior of
each contenders during their participation in the contest. In the initial phase, the system 101

observes the behavior of the contenders 107 with an intention to generate a compatibility model 206. The compatibility model 206 may be based on machine learning which learns about the behavior and compatibility between the contenders 107 over the time and applying the same during the real-time. In the upcoming paragraphs, how the compatibility model 206 is generated in
plained in detail.
At first, the system 101 may set a plurality of contest optimisation parameters 203 corresponding to the contest being participated by the plurality of contenders 107. According to an embodiment, the plurality of contest optimisation parameters 203 may include, but not limited to, retention time and ) engagement level. The retention time may comprise a time duration for which at least a pair of contenders of the plurality of contenders 107 may participate in the contest. Whereas the engagement level may comprise interaction of at least one contender 107 with other contenders 107 while participating in the contest and interaction with features configured in the contest. For example, the one contender 107 may talk or chat with the other contender 107 showing his/her interest/engagement
in the contest. In another example, the contender 107 may interact with different features of the
contest, for example, pressing a like button, and providing a comment. The system 101 analyzes the
plurality of contenders 107, while participating in the contest, relative to the plurality of contest
optimisation parameters 203. The analysis may be done for a predefine time-period, for example, 1
day, 1 week, or 1 month.
Based on the analyzing, the system 101 now generates a contender matrix 204 comprises a plurality
of matrix values such that each matrix value indicates a preliminary level of matching between a pair
of contenders of the plurality of contenders. According to an embodiment, the contender matrix 204
may be a Boolean matrix as shown below, where CI, C2, C3 Cn comprises the plurality of
contenders

CI C2 C3
Cn

CI C2 C3 ... Cn
0 110 0
10 0 0 0
0 0 0 0 1
0 10 10

The contender matrix 204 generates gives an indication how well one contender 107 is compatible with other contenders 107. For example, as can be seen from the above contender matrix 204, the matrix value "0" at index (i, j) indicates that contender "i" of the plurality of contenders 107 "not being matched" to contest with contender "j". Similarly, the matrix value "1" at index (i, j) indicates that the contender "i' of the plurality of contenders 107 "being matched" to contest with the contender "j". It may be understood to a skilled person that the above discussed contender matrix 204 in a form of Boolean matrix is merely an example, and the contender matrix 204 may be generated in different forms. Post generating the contender matrix 204, the system 101 now generates contender data 205 for each of the plurality of contenders 107 based on the participation of the plurality of contenders 107 in the contest. The contender data 205 may include, but limited to, skill data, style data, and profile data. In another embodiment, the contender data 205 may comprise the updated contender data 205 for the set of contenders at the instance. In an embodiment, the skill vector may be determined by the determining unit 212 from the skill data of each contender 107 based on win and loss data of each contender 107 of the set of contenders. The skill data in an embodiment may comprise all the skill data from the time of registration of profile of the contender. The skill data in another embodiment may comprise the skill data of a contender for a predefined span of time.
In an embodiment, the style data of a contender 107 corresponds to the manner with which each of the contenders 107 participate in the contest. The style data may comprise contest specific data corresponding to each contender of the plurality of contenders 107 that captures the style of the contender 107 when participating in the contest. In other words, the determining unit may be configured to determine style vector from the style data of each contender 107 in the set of contenders

based on the manner with which each of the contender 107 participate in the contest. For example if the contest in an embodiment is a carroms game, the style data may comprise one or more of (a) average distance of shots (b)average time taken/shot (c) average number of coins/shot etc...
i In an embodiment, the profile data may comprise contender specific data. In other words, the determining unit may be configured to determine the profile vector for each contender based on one or more of statistical data related to profile of each contender in the set of contenders. For example the profile data may comprise, (a) number of contests participated, (b)Number of contests won, (c) New contender or old contender (d) Frequent participant of the contest or sparse/rare participant of
the contest etc... In an embodiment of the invention, the integrated consideration of style and profile data provides a holistic modeling to determine contender preference and behavior in the perspective of the contest.
The generation of the contender matrix 204 and the contender data 205 not only helps the system 101 to understand about the behaviors of the contenders 107 participating in the contest but also helps in
understanding their compatibility between them for a contest. Hence, the system 101 generates and
trains the compatibility model 206 based on the contender matrix 204 and the contender data 205. It
may be understood to the skilled person that the training of the compatibility model 206 is continuous
process i.e., the compatibility model 206 keeps on learning and updating itself based on the future
behavior of the existing or even new contenders 107 registering and participating in the contest. The
continuous learning of the compatibility model 206 helps the system 101 to identify the best matching or best compatible contenders in the real-time, which is now explained in upcoming paragraphs of the specification.
For example, in an embodiment, where the contender matrix is a Boolean matrix (the contender
matrix can be a non-Boolean matrix as well) and the number of plurality of contenders is K in the
contender access platform. So the size of the contender matrix is [KxK], and a matric value at each
position of the matrix determines the preliminary level matching of a pair of contenders. For example
in this embodiment of contender matrix 204 is [KxK] then,
(a) the matrix value "0" at index (i, j) indicates that contender "i" of the plurality of contenders, ) should not be matched to contender "j";

b) the matrix value "1" at index (i, j) indicates that contender "i' of the plurality of contender, can be matched to play "j".
In another embodiment of the invention, the contender matrix to satisfying contest optimisation
parameters may comprise for example "Elo rating" with a preset condition of "+/- "k". Then, the
matrix value of the position (i,j) in the contender matrix may be marked with a matrix value "1" if
the "Elo rating" of contender in "ith" place in the row is within the present condition of contest
parameter "+/- "k" in comparison to the contender in column "j".
Similarly, in another embodiment the contest optimisation parameters 203 may comprises any other optimization function for example based on "Win rates", which identifies allowed pairing of the contenders optimizing on desired contest optimisation parameters goals.
In the real-time implementation, detecting unit 212 may detect a set of contenders, from the plurality
of contenders 107, that are willing to participate in the contest at a particular time instance. That is,
the detecting unit 212 may for example be configured to detect all the contender accessing the contest
access platform at a particular time instance. Once the set of contenders are detected participating in
the contest, in next step, the determining unit 213. may detect a plurality of contender vectors 207
corresponding to each of the contenders from the set of contenders. According to an embodiment,
the plurality of contender vectors 207 may include, but not limited to, skill vector, style vector and profile vector. The determining unit 213 may determine the skill vector for each contender based on the skill data (as discussed above) comprising at least one of a win and lose data with each contender. Similarly, the determining unit 213 may determine the style vector based on the style data (as discussed above) of each contender indicating a manner in which each contender participates in the
contest. Similarly, the determining unit 213 may determine the profile vector for each contender
based on one or more of statistical data (as discussed above) related to profile of each contender. The
objective of determining the contender vectors 207 is understand the real-time behavior of the
contenders 107 during the implementation.

Now since the system 101 is already have the trained compatibility model 206 which was made based on the past behavior of contenders 107 while participating in the contest, this helps the system 101 to take proper decision while determining the compatibility in the real-time. Hence, in the next step, the applying unit 214 may apply the pretrained compatibility model 206 upon the contender vectors
207 of each of the contenders 107 to determine a plurality of compatibility scores 208 for each contender. The plurality of compatibility scores 208 determined for each contender may indicate compatibility level of each contender 107 with other contenders 107 of the set of contenders 107. As discussed above, the compatibility model 206 may be a deep learning model based on matching function to which the contender vectors 207 are provided to an input layer to consequentially identify
compatible contenders.
Finally, the identifying unit 215 identify at least a pair of contenders 107, amongst the set of contenders 107, based on the plurality of compatibility scores 208 determined for each contender of
the set of contenders by applying the compatibility model 206. In an embodiment, the pair of
contenders indicates those contenders having highest level of matching for the contest amongst the
set of contenders. Considering five set of contenders (A, B, C, D, and E) are analyzed while
participating in the contest, it may be observed that, based on compatibility scores 208, the contender
A is best match with contender D. Hence, the contender A and D are identified as a pair of contenders
having highest level of matching amongst other contenders B, C and E. It may be understood to a person skilled in art that above considered scenario is merely an example, and there may be different permutation and combination in which the contenders may be identified as the compatible contenders.
Upon identifying the at least a pair of compatible contenders, the identified pairs of contenders may
proceed to participate in the contest. Also, the compatibility model 206 keeps on observing the
behavior of the identified pair of compatible contenders while they participate in the contest. Based
on the observation, the compatibility model 206 learns about the compatibility of the identified pairs
of contenders and update itself accordingly. This way, the present disclosure not only identifies the
compatible contenders but also keeps them engaged while participating in the contest.

Figure 3 illustrates a flowchart describing a method of determining compatible contenders in the contest accordance with an embodiment of the present invention.
As illustrated in Figure.3, the method 300 includes one or more blocks illustrating determining
compatible contenders in the contest. The method 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, units and functions,
which perform specific functions or implement specific abstract data types.
The order in which the method is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods 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.
At block 301, the method 300 may include detecting a set of contenders, from a plurality of contenders that are willing to participate in the contest at an instance.
At block 302, the method 300 may include, determining a plurality of contender vectors 207 ) corresponding to each contender 107 of the set of contenders. In an embodiment, the plurality of contender vectors 207 comprises at least one of a skill vector, a style vector and a profile vector.
At block 303, the method 300 may include applying a pretrained compatibility model 206 upon the plurality of contender vectors 207 to determine a plurality of compatibility scores 208 for each
contender. In an embodiment, the plurality of compatibility scores 208 determined for each
contender indicates compatibility level of each contender with other contenders of the set of
contenders.
At block 304, the method 300 may include identifying at least a pair of contenders, amongst the
set of contenders, based on the plurality of compatibility scores 208 determined for each contender
of the set of contenders. In an embodiment, the at least a pair of contenders indicates those

contenders having highest level of matching for the contest amongst the set of contenders. Further, the compatibility model 206 learns about the compatibility of the set of contenders based on the identifying, and thereby updating the compatibility model 206 with the compatibility of the set of contenders. i
A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary, a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention.
) When a single device or article is described herein, it will be clear that more than one device/article (whether they cooperate) may be used in place of a single device/article. Similarly, where more than one device or article is described herein (whether they cooperate), it will be clear that a single device/article may be used in place of the more than one device or article or a different number of devices/articles may be used instead of the shown number of devices or programs. The
> functionality and/or the features of a device may be alternatively embodied by one or more other
devices which are not explicitly described as having such functionality/features. Thus, other
embodiments of the invention need not include the device itself.
Finally, the language used in the specification has been principally selected for readability and ) instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the embodiments of the present invention are intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.
> While various aspects and embodiments have been disclosed herein, other aspects and embodiments
will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein
are for purposes of illustration and are not intended to be limiting, with the true scope and spirit
being indicated by the following claims.

Advantages of the embodiment of the present disclosure are illustrated herein:
a. Enhancing the contender experience of participating a contest.
b. Satisfies the preset parameters of business level optimization.

Referral Numerals:

Reference Number Description
100 Environment
101 System
102 Processor
103 Memory
104 I/O interface
105 Communication Network
106 (106-1, 106-2, 106-3... 106-n) Plurality of Contender devices
107 (107-1, 107-2, 107-3... 107-n) Plurality of Contenders
202 Data
203 Contest optimisation parameters
204 Contender matrix
205 Contender data
206 Compatibility model
207 Contender vector
208 Compatibility scores
209 Other data
211 Units
212 Detecting unit
213 Determining unit
214 Applying unit
215 Identifying unit
301-304 Method steps

We Claim:
1. A method of determining compatible contenders for a contest, the method comprising:
detecting a set of contenders (107), from a plurality of contenders (107) that are willing to participate in the contest at an instance;
determining a plurality of contender vectors (207) corresponding to each contender of the set of contenders, wherein the plurality of contender vectors (207) comprises at least one of a skill vector, a style vector and a profile vector;
applying a pretrained compatibility model (206) upon the plurality of contender vectors (207) to determine a plurality of compatibility scores (208) for each contender (107), wherein the plurality of compatibility scores determined for each contender (107) indicates compatibility level of each contender with other contenders of the set of contenders; and
identifying at least a pair of contenders, amongst the set of contenders (107), based on the plurality of compatibility scores (208) determined for each contender of the set of contenders, wherein the at least a pair of contenders (107) indicates those contenders having highest level of matching for the contest amongst the set of contenders (107), and
wherein the compatibility model (206) further learns about the compatibility of the set of contenders (107) based on the identifying, thereby updating the compatibility model (206) with the compatibility of the set of contenders (107).
2. The method as claimed in claim 1, wherein the compatibility model is trained by:
setting a plurality of contest optimisation parameters (203) corresponding to the contest being participated by the plurality of contenders (107), wherein the plurality of contest optimisation parameters (203) comprises at least one of retention time and engagement level;
analyzing the plurality of contenders (107), while participating in the contest, relative to the plurality of contest optimisation parameters (203);
generating a contender matrix (204) based on the analyzing, wherein the contender matrix (204) comprises a plurality of matrix values such that each matrix value indicates a preliminary level of matching between a pair of contenders of the plurality of contenders (107);
generating contender data (205) for each of the plurality of contenders based on the participation of the plurality of contenders in the contest, wherein the contender data comprises at least one of skill data, style data, and profile data; and
training the compatibility model (206) based on the contender matrix (204) and the contender data (205).
3. The method as claimed in claim 2, wherein the retention time comprises a time duration for which at least a pair of contenders of the plurality of contenders (107) participate in the contest, and the engagement level comprises interaction of at least one contender (107) with other contenders (107) participating in the contest and interaction with features associated with the contest.
4. The method as claimed in claim 2, wherein the contender matrix (204) is a Boolean matrix, wherein,

matrix value "0" at index (i, j) indicates that contender "i" of the plurality of contenders (107) not being matched to contest with contender "j";
matrix value "1" at index (i, j) indicates that the contender "i' of the plurality of contenders (107) being matched to contest with the contender "j". i
5. The method as claimed in claim 1, wherein the method further comprises:
determining the skill vector for each contender (107) based on the skill data
comprising at least one of a win data and lose data associated with each contender (107);
) determining the style vector based on the style data, of each contender (107),
indicating a manner in which each contender (107) participates in the contest; and
determining the profile vector for each contender (107) based on one or more of statistical data related to profile of each contender (107).
> 6. A system (101) for determining compatible contenders for a contest, the system comprising,
detecting unit (212) to detect a set of contenders (107), from the plurality of contenders (107) that are willing to participate in the contest at an instance;
determining unit (213) to determine a plurality of contender vectors (207)
) corresponding to each contender of the set of contenders (107), wherein the plurality of
contender vectors (207) comprises at least one of a skill vector, a style vector and a profile vector;
applying unit (214) to apply a pretrained compatibility model (206) upon the plurality of contender vectors (207) to determine a plurality of compatibility scores (208)
> for each contender (107), wherein the plurality of compatibility scores (208) determined for
each contender indicates compatibility level of each contender with other contenders of the
set of contenders (107); and
identifying unit (215) to identify at least a pair of contenders, amongst the set of
contenders (107), based on the plurality of compatibility scores (208) determined for each
) contender of the set of contenders (107), wherein the at least the pair of contenders indicates
those contenders having highest level of matching for the contest amongst the set of
contenders (107), and
wherein the compatibility model (206) is configured to learn about the compatibility
of the set of contenders based on the identifying, thereby updating the compatibility model
i (206) with the compatibility of the set of contenders (107).
7. The system (101) as claimed in claim 6, trains the compatibility model (206) by:
setting a plurality of contest optimisation parameters (203) corresponding to the
contest being participated by the plurality of contenders (107), wherein the plurality of
) contest optimisation parameters (203) comprises at least one of retention time and
engagement level;
analyzing the plurality of contenders (107), while participating in the contest, relative to the plurality of contest optimisation parameters (203);
generating a contender matrix (204) based on the analyzing, wherein the contender
> matrix (204) comprises a plurality of matrix values such that each matrix value indicates a

preliminary level of matching between a pair of contenders of the plurality of contenders (107);
generating a contender data (205) for each of the plurality of contenders (107) based on the participation of the plurality of contenders (107) in the contest, wherein the contender
> data (205) comprises at least one of skill data, style data, and profile data; and
training the compatibility model (206) based on the contender matrix (204) and the contender data (205).
8. The system (101) as claimed in claim 7, wherein the retention time comprises a time
) duration for which at least a pair of contenders of the plurality of contenders (107)
participate in the contest, and the engagement level comprises interaction of at least one
contender (107) with other contenders (107) participating in the contest and interaction with
features configured in the contest.
> 9. The system (101) as claimed in claim 7, wherein the contender matrix (204) is a Boolean
matrix, wherein,
the matrix value "0" at index (i, j) indicates that contender "i" of the plurality of contenders (107) not being matched to contest with contender "j";
the matrix value "1" at index (i, j) indicates that contender "i' of the plurality of
) contender (107) being matched to contest with contender "j".
10. The system (101) as claimed in claim 6, wherein the determining unit (213) is further configured to:
determine the skill vector for each contender (107) based on the skill data
i comprising at least one of a win and lose data with each contender (107);
determine the style vector based on the style data of each contender (107) indicating a manner in which each contender (107) participates in the contest; and
determine the profile vector for each contender (107) based on one or more of statistical data related to profile of each contender (107). )