FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003
COMPLETE SPECIFICATION (See Section 10 and Rule 13)
Title of invention:
SYSTEMS AND METHODS FOR AUTOMATED VALIDATION OF VISUAL SIMILAR ENTITIES
Applicant
Tata Consultancy Services Limited A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India
Preamble to the description
The following specification particularly describes the invention and the manner in which it is to be performed.

TECHNICAL FIELD [001] The disclosure herein generally relates to validation techniques, and, more particularly, to systems and methods for automated validation of visual similar entities.
BACKGROUND
[002] Every industry is trying to find a way to attract new users/buyers and work towards retention of their existing customers to enhance and/or expand their operations and business. As globalization takes over the world, the organizations are also trying to implement new strategies in order to expand their businesses across nations. The first step one takes towards this goal is, providing suggestions/recommendations of the new/existing products to customers based on their behavior analytics. Recommendations are widely used in different fields including retail stores, e-commerce websites, healthcare, travel and tourism, finance, social media, digital entertainment platforms / applications, etc.
[003] There are various mathematical and proven algorithmic approaches to provide suggestions / recommendations of related product / commodity in today’s scenario. The training data is generally behavioral data of the customers and attributes of the products. However, there may not be a validation of test data. Hence, classification / collaborative filtering algorithms are generally an unsupervised / semi-supervised learning approach. Hence, validation of results become slightly complex and need to re-produce a parallel prediction set to arrive at a comparison score. Commonly the validation of such unsupervised / semi-supervised learning are done by two methods: (i) Beta testing of the algorithm for a segmented group of customers or on all customers for a stipulated time period wherein field testing phase which is a user exposed method ii) validating the recommendation results with a manually defined test output. Both of the above conventionally known approaches involving heavy computations, large amount of time consumption and pre-training of systems thus leading to additional cost.

SUMMARY
[004] Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one aspect, there is provided a processor implemented method of automatically validating visual similar entities. The method comprises obtaining via one or more hardware processors, an input comprising one or more entities; generating via the one or more hardware processors, one or more data dictionaries of a plurality of attributes specific to the one or more entities; determining via the one or more hardware processors, a relative weight for each of the plurality of attributes specific to the one or more entities, wherein the relative weight is a representation of inter-relation between two or more attributes of the plurality of attributes of each of the one or more entities; computing via the one or more hardware processors, a cumulative weight of the plurality of attributes based on the determined relative weight; performing via the one or more hardware processors, a one-hot encoding on the plurality of attributes based on the relative weight and the cumulative weight to generate a resultant matrix, wherein the resultant matrix comprises a weight for each of the plurality of attributes; generating via the one or more hardware processors, a test case based on the generated resultant matrix and associated transpose thereof, wherein the generated test case comprises the one or more entities and corresponding one or more similar entities recommended for each of the one or more entities; obtaining via the one or more hardware processors, a predicted result generated by a recommendation engine, wherein the predicted result comprises one or more recommended entities; and performing via the one or more hardware processors, a comparison of (i) the generated test case and (ii) the predicted result to obtain an analytics report comprising at least one of accurate results and inaccurate results and to validate the recommendation engine and the predicted result based on the comparison.
[005] In one embodiment, the inter-relation between the two or more attributes is derived based on a relative distance that is directly proportional to similarity and ratio of the two or more attributes of the one or more entities.

[006] In one embodiment, the plurality of attributes comprised in the one or more dictionaries are arranged in an order based on an associated value thereof.
[007] In an embodiment, the method may further comprise generating a score for the accurate results, wherein the score is indicative of a qualitative validation of the recommendation engine.
[008] In an embodiment, the method may further comprise correcting the inaccurate results based on the comparison and providing at least one of corrected results and one or more observations to the recommendation engine for generating subsequent prediction results.
[009] In another aspect, there is provided a processor implemented system for automatically validating visual similar entities. The system comprises a memory storing instructions; one or more communication interfaces; and one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to: obtain an input comprising one or more entities; generate one or more data dictionaries of a plurality of attributes specific to the one or more entities; determine a relative weight for each of the plurality of attributes specific to the one or more entities, wherein the relative weight is a representation of inter-relation between two or more attributes of the plurality of attributes of each of the one or more entities; compute a cumulative weight of the plurality of attributes based on the determined relative weight; perform a one-hot encoding on the plurality of attributes based on the relative weight and the cumulative weight to generate a resultant matrix, wherein the resultant matrix comprises a weight for each of the plurality of attributes; generate a test case based on the generated resultant matrix and associated transpose thereof, wherein the generated test case comprises the one or more entities and corresponding one or more similar entities recommended for each of the one or more entities; obtain a predicted result generated by a recommendation engine, wherein the predicted result comprises one or more recommended entities; and perform a comparison of (i) the generated test case and (ii) the predicted result to obtain an analytics report

comprising at least one of accurate results and inaccurate results and to validate the recommendation engine and the predicted result based on the comparison.
[010] In one embodiment, the inter-relation between the two or more attributes is derived based on a relative distance that is directly proportional to similarity and ratio of the two or more attributes of the one or more entities.
[011] In one embodiment, the plurality of attributes comprised in the one or more dictionaries are arranged in an order based on an associated value thereof.
[012] In an embodiment, the one or more hardware processors are further configured by the instructions to generate a score for the accurate results, wherein the score is indicative of a qualitative validation of the recommendation engine.
[013] In an embodiment, the one or more hardware processors are further configured by the instructions to correct the inaccurate results based on the comparison and providing at least one of corrected results and one or more observations to the recommendation engine for generating subsequent prediction results.
[014] In yet another aspect, there are provided one or more non-transitory machine readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause automatic validation of visual similar entities by obtaining via the one or more hardware processors, an input comprising one or more entities; generating via the one or more hardware processors, one or more data dictionaries of a plurality of attributes specific to the one or more entities; determining via the one or more hardware processors, a relative weight for each of the plurality of attributes specific to the one or more entities, wherein the relative weight is a representation of inter-relation between two or more attributes of the plurality of attributes of each of the one or more entities; computing via the one or more hardware processors, a cumulative weight of the plurality of attributes based on the determined relative weight; performing via the one or more hardware processors, a one-hot encoding on the plurality of attributes based on the relative weight and the cumulative weight to generate a resultant matrix, wherein the resultant matrix comprises a weight for each of the plurality of attributes; generating via the one or

more hardware processors, a test case based on the generated resultant matrix and associated transpose thereof, wherein the generated test case comprises the one or more entities and corresponding one or more similar entities recommended for each of the one or more entities; obtaining via the one or more hardware processors, a predicted result generated by a recommendation engine, wherein the predicted result comprises one or more recommended entities; and performing via the one or more hardware processors, a comparison of (i) the generated test case and (ii) the predicted result to obtain an analytics report comprising at least one of accurate results and inaccurate results and to validate the recommendation engine and the predicted result based on the comparison.
[015] In one embodiment, the inter-relation between the two or more attributes is derived based on a relative distance that is directly proportional to similarity and ratio of the two or more attributes of the one or more entities.
[016] In one embodiment, the plurality of attributes comprised in the one or more dictionaries are arranged in an order based on an associated value thereof.
[017] In an embodiment, the instructions which when executed by the one or more hardware processors may further cause generating a score for the accurate results, wherein the score is indicative of a qualitative validation of the recommendation engine.
[018] In an embodiment, the instructions which when executed by the one or more hardware processors may further cause correcting the inaccurate results based on the comparison and providing at least one of corrected results and one or more observations to the recommendation engine for generating subsequent prediction results.
[019] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
BRIEF DESCRIPTION OF THE DRAWINGS

[020] 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 principles:
[021] FIG. 1 depicts an exemplary block diagram of a validation system for automatically validating visual similar entities, in accordance with an embodiment of the present disclosure.
[022] FIG. 2 depicts an exemplary flow chart depicting automated validation of visual similar entities using the system of FIG. 1 in accordance with an embodiment of the present disclosure.
[023] FIG. 3 is an exemplary flow diagram illustrating a method for automatically validating of visual similar entities using the system of FIG. 1, in accordance with an embodiment of the present disclosure.
DETAILED DESCRIPTION OF EMBODIMENTS [024] Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope being indicated by the following claims.
[025] Referring now to the drawings, and more particularly to FIGS. 1 through 3, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.
[026] FIG. 1 depicts an exemplary block diagram of a validation system 100 for automatically validating visual similar entities, in accordance with an embodiment of the present disclosure. The system 100 may also be referred as

‘entities validation system’ and may be interchangeably used hereinafter. In an embodiment, the system 100 includes one or more hardware processors 104, communication interface device(s) or input/output (I/O) interface(s) 106 (also referred as interface(s)), and one or more data storage devices or memory 102 operatively coupled to the one or more hardware processors 104. The one or more processors 104 may be one or more software processing components and/or hardware processors. In an embodiment, the hardware processors can 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(s) is configured to fetch and execute computer-readable instructions stored in the memory. In an embodiment, the system 100 can be implemented in a variety of computing systems, such as laptop computers, notebooks, hand-held devices, workstations, mainframe computers, servers, a network cloud and the like.
[027] The I/O interface device(s) 106 can include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like and can facilitate multiple communications within a wide variety of networks N/W and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. In an embodiment, the I/O interface device(s) can include one or more ports for connecting a number of devices to one another or to another server.
[028] The memory 102 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. In an embodiment, a database 108 is comprised in the memory 102, wherein the database 108 comprises information, for example, entities, associated attributes, inter-relationship between attributes, distance information between the attributes, relative weights, cumulative weights, resultant matrix, test cases, predicted results,

dictionaries, validation results pertaining to recommendation model that are indicative of accurate and inaccurate results, score for the accurate results, type of correction made for the inaccurate results, feedback, and the like. In an embodiment, the memory 102 may store (or stores) one of more techniques (e.g., one hot encoder, score generator, weight calculator, resultant matrix generator, validator, and the like). The memory 102 further comprises (or may further comprise) information pertaining to input(s)/output(s) of each step performed by the systems and methods of the present disclosure. More specifically, information pertaining to entities (e.g., product information) obtained from sources (e.g., users, and the like), and the like, may be stored in the memory 102. In other words, input(s) fed at each step and output(s) generated at each step are comprised in the memory 102, and can be utilized in further processing and analysis.
[029] FIG. 2, with reference to FIG. 1, depicts an exemplary flow chart depicting automated validation of visual similar entities using the system 100 of FIG. 1 in accordance with an embodiment of the present disclosure.
[030] FIG. 3, with reference to FIGS. 1-2, is an exemplary flow diagram illustrating a method for automatically validating of visual similar entities using the system 100 of FIG. 1, in accordance with an embodiment of the present disclosure. In an embodiment, the system(s) 100 comprises one or more data storage devices or the memory 102 operatively coupled to the one or more hardware processors 104 and is configured to store instructions for execution of steps of the method by the one or more processors 104. The steps of the method of the present disclosure will now be explained with reference to components of the system 100 of FIG. 1, the flow chart of FIG. 2, and the flow diagram as depicted in FIG. 3. At step 302 of the present disclosure, the one or more hardware processors 104 obtain an input comprising one or more entities. The one or more entities comprise, but are not limited to information on products, and the like and shall not be construed as limiting the scope of the present disclosure. At step 304 of the present disclosure, the one or more hardware processors 104 generate one or more data dictionaries of a plurality of attributes specific to the one or more entities. Data dictionary in the present disclosure refers to a

handbook/manual of product attributes and organized format of the same based on their inter-relations inside each attribute as a list. In other words, their relative distance is directly proportional to their similarity and ratio. More specifically, the inter-relation(s) between the two or more attributes is/are derived based on a relative distance that is directly proportional to similarity and ratio of the two or more attributes of the one or more entities. FIG. 2 depicts dictionary (or data dictionary) generation at step 202. Assuming that an entity type is a footwear, one or more data dictionaries of a plurality of attributes specific to this entity type are generated. In an embodiment, data dictionary is a JavaScript Object Notation (JSON) file and shall not be construed as limiting the scope of the present disclosure. Below is an exemplary dictionary and attributes associated thereof: color dictionary: {
blue_range:{ Turkish blue, sky blue, steel blue, sapphire blue, blue,
navy blue},
red_range: {wine red, blood red, ruby, cherry, scarlet, crimson red,
red, rose, blush} } heel_height =['flat','low','mid','high'] fit=['wide','regular','extra wide', 'extra-wide']
style=['ankle boot', 'ankle strap','ballerina slipper','ballerina','ballet pump', 'boat shoe', 'brogue', 'chelsea ankle boot','chelsea', 'court', 'cross over strap', 'espadrille', 'flip flop', 'over the knee boots','knee boot', 'loafer', 'mid calf boot','moccasin slipper','moccasin','mule sandal', 'mule slipper','mule', 'peep toe', 'pump','slingback sandal', 'sandal','sandals', 'shoe boot', 'slider', 'slingback shoe', 'slipper boot', 'slipper sock', 't bar', 'thigh high boot', 'trainer', 'walking boots', 'wellies', 'wellington boots']
fw_catg=['shoe','slipper','trainer','low boot','knee boot','boot', 'court','loafer','sandal','pump'] heel_type=['flatform','kitten','round','platform','wedg','statement','block','stiletto']
[031] At step 306 of the present disclosure, the one or more hardware processors 104 determine a relative weight for each of the plurality of attributes

specific to the one or more entities. Step 204 of FIG. 2 depicts relative weight calculator. In the present disclosure, the relative weight is a representation of inter-relation between two or more attributes of the plurality of attributes of each of the one or more entities.
Relative weight refers to a constant that attributes to the maximum weight that can be assigned to a closely related attribute. Present disclosure and its system implements a relative weight calculator (stored in the memory 102) wherein it is an iterator which assigns the maximum relative weight to the closest attribute and thereon decreases by the iterator value and assigns the same to the attributes that are in lesser proximity. It is to be noted by a person having an ordinary skill in the art or person skilled in the art that the unlike attributes that possess a different key do not gain any weights. This way the system 100 of the present disclosure differentiates the like and unlike attributes.
[032] The ordering of the dictionary values is also necessary as the weight of the related attribute tends to be relatively low when compared to an actual attribute, whereas, the weight of the irrelevant attribute tends to be 0 (zero). i.e., from above example, if the original color of the product is sky blue, products that have sky blue have weight of 1 (one). Products that have color as Turkish blue and steel blue may have weight of 0.5. Products that has sapphire blue color may be weighted as 0.49, for blue it can be 0.48, and for navy blue say 0.47. However, the products that has color in red_range tend to have color value as 0 (zero). This weight is referred as a relative weight of the product attribute. Below is an exemplary table (Table 1) of products (or product identifiers) for which relative weight is calculated:

Table 1
Product ID Red Light Red Brick Red Blue Green Yellow
123456 0.99 1 0.98 0 0 0
234567 1 0.99 0.99 0 0 0

345678 0 0 0 1 0 0
456789 0 0 0 0 0 1
[033] At step 308 of the present disclosure, the one or more hardware processors 104 compute a cumulative weight of the plurality of attributes based on the determined relative weight. In the present disclosure, cumulative weight refers to a constant value. If product has a specific attribute, the weight is assigned, else it becomes 0 (zero). It is to be noted by a person having an ordinary skill in the art or person skilled in the art that cumulative weight is heavier than the relative weight. The present disclosure and its system 100 implements a cumulative weight calculator (comprised in the memory 102) which sums up the relative weight and cumulative weight. Step 206 of FIG. 2 depicts cumulative weight calculator. Below is an exemplary table (Table 2) of products (or product identifiers) for which cumulative weight is calculated.

Table 2
Product ID Red Light Red Brick Red Blue Green Yellow
123456 0 3 0 0 0 0
234567 3 0 0 0 0 0
345678 0 0 0 3 0 0
456789 0 0 0 0 0 3
[034] At step 310 of the present disclosure, the one or more hardware processors 104 perform a one-hot encoding on the plurality of attributes based on the relative weight and the cumulative weight to generate a resultant matrix, wherein the resultant matrix comprises a weight for each of the plurality of attributes. Below is an exemplary one hot encoding performed by the present

disclosure and its system and method and shall not be construed as limiting the scope of the present disclosure:
f (x)= Cumulative weight of the product x = Boolean value. If attribute is present =1, else 0. n = number of attributes w = relative weight of the attribute. ow = actual weight of the attribute.
[035] The present disclosure and its system 100 of FIG. 1 performs one-hot encoding of the attributes and forms a matrix. Bi-modal matrix is generated is a resultant of one hot encoder (comprised in the memory 102 of FIG. 1). Step 208 of FIG. 2 depicts resultant matrix generation by performing one hot encoding on attributes. Below is an exemplary table (Table 3) of products depicting a resultant matrix generated:

Table 3
P1 P2 P3 P4 P5
P1 20 12 17 6 0
P2 12 20 1 13 5
P3 17 1 20 4 11
P4 6 13 4 20 17
P5 0 5 11 17 20
[036] At step 312 of the present disclosure, the one or more hardware processors 104 generate a test case based on the generated resultant matrix and associated transpose thereof, wherein the generated test case comprises the one or more entities and corresponding one or more similar entities recommended for each of the one or more entities. Step 210 of FIG. 2 depicts a test case generated

or derived from the generated resultant matrix and associated transpose thereof. More specifically, the present disclosure and its system 100 implemented a matrix multiplier (stored in the memory 102) that when executed generates a test case by multiplying the generated resultant matrix with a transpose of the generated resultant matrix. In other words, the matrix multiplier performs multiplication of original and transpose matrices and arranges the output row as per the weights order. Below table 4 depicts an exemplary test case generated by the system 100, and illustrated as a way of non-construing example:

Table 4
P1 P1 P3 P2 P4 P5

20 17 12 6 0
P2 P2 P4 P1 P5 P3

20 13 12 5 1
P3 P3 P1 P5 P4 P2

20 17 11 4 1
P4 P4 P5 P2 P1 P3

20 17 13 6 4
P5 P5 P4 P3 P2 P1

20 17 11 5 0
[037] At step 314 of the present disclosure, the one or more hardware
processors 104 obtain a predicted result generated by a recommendation engine,
wherein the predicted result comprises one or more recommended entities. FIG. 2
depicts receiving predicted result from the recommendation engine.
Recommendation engine can be any algorithm/model
(Supervised/unsupervised/semi-Supervised) that gives a predicted result for a recommendation or personalization or classification use case.
[038] At step 316 of the present disclosure, the one or more hardware processors 104 perform a comparison of (i) the generated test case and (ii) the predicted result to obtain an analytics report comprising at least one of accurate results and inaccurate results and to validate the recommendation engine and the predicted result based on the comparison. More specifically, the present disclosure and its system 100 of FIG. 1 implement a result matcher (stored in the memory

102 of FIG. 1) to perform a comparison of (i) the generated test case and (ii) the
predicted result to obtain an analytics report comprising at least one of accurate
results and inaccurate results and to validate the recommendation engine and the
predicted result based on the comparison. Step 212 of FIG. 2 depicts result
matcher or comparison of the predicted result with the generated test case,
wherein the comparison depicts validation of the resultant of recommendation
engine/model and matrix multiplier and identifies the products/entities present in
the recommendation result (predicted result) is same as matrix multiplier output
(test case) that has been generated using mathematical derivation. The comparison
further indication position of the product / entity in both Predicted result and Test
case. Based on the above condition number of hits and/or miss are calculated.
Below is an exemplary technique as implemented by the present disclosure and its
system and method for accurate results computation and shall not be construed as
limiting the scope of the present disclosure:
accuracy=(sum(scores)/(count_prod*(min(n_pred, n_test))))*100
sum(scores) : sum of scores obtained for each product when compared against model prediction output and validation code predicted output. Count_prod: Total Number of products in catalogue. n_pred: No. of products in model predicted list. n_test: No. of products in validation code predicted list.
[039] Further, the system 100 generate a score for the accurate results, wherein the score is indicative of a qualitative validation of the recommendation engine. The system 100 further corrects the inaccurate results based on the comparison and providing at least one of corrected results and one or more observations to the recommendation engine for generating subsequent prediction results. In other words, the present disclosure and its system 100 of FIG. 1 implements a defect analyser (comprised in the memory 102 of FIG. 1), wherein the defect analyser (or the validation system 100) validates the miss hits in the Predicted result versus test case. A Thesaurus of intricate entity attribute mapping is generated against the recommended products / entities. This helps to modify /

tune the External Recommendation Engine accordingly. The above description may be better understood by way of following non-construing example: For instance, score calculation for determining accurate results and/or inaccurate results: Total No. of items in the test result/test case versus Total No. of items in the predicted result of the recommendation engine. For example, say in a test case, P1: P2, P3, P4; predicted result by any recommendation engine for P1: P2, P3, P5, then the score computed by the system 100 is 2/3 wherein for P1: similar entities that are obtained and overlap are P2 and P3 (products P2 and P3). Accuracy: (Total Score obtained by the predicted results / Total No of items) * 100. It is to be understood by a person having ordinary skill in the art or person skilled in the art the above score computation shall not be construed as limiting the scope of the present disclosure. This individual score is assigned towards them / the master product (say P1) and positioning determines accuracy and inaccurate data along with detailed metrics derived from the data versus features - which then symptom the cause for specific accuracy dropping that resolves and feedback to the main engine (e.g., the recommendation engine). In other words, say in the case of incorrect attributed colour – where it is actual Blue, and could be mentioned as Green. This sort of difference in result lowers down the contour and map more with Green colored items whereas it has to match with Blue. This observation includes a feedback that may involve (simple/complex) data correction that created disintegrated score(s) on original recommendation. The above steps 302 till 316 including performing comparison as described herein in the present disclosure to validate the recommendation engine and the predicted result is referred as automatic validation of visual similar entities.
[040] The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.

[041] It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g. any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g. hardware means like e.g. an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g. an ASIC and an FPGA, or at least one microprocessor and at least one memory with software processing components located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g. using a plurality of CPUs.
[042] The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various components described herein may be implemented in other components or combinations of other components. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
[043] The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative

boundaries can be defined so long as the specified functions and relationships
thereof are appropriately performed. Alternatives (including equivalents,
extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.
[044] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[045] It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated by the following claims.

We Claim:
1. A processor implemented method, comprising:
obtaining via one or more hardware processors, an input comprising one or more entities (302);
generating via the one or more hardware processors, one or more data dictionaries of a plurality of attributes specific to the one or more entities (304);
determining via the one or more hardware processors, a relative weight for each of the plurality of attributes specific to the one or more entities (306), wherein the relative weight is a representation of inter-relation between two or more attributes of the plurality of attributes of each of the one or more entities;
computing via the one or more hardware processors, a cumulative weight of the plurality of attributes based on the determined relative weight (308);
performing via the one or more hardware processors, a one-hot encoding on the plurality of attributes based on the relative weight and the cumulative weight to generate a resultant matrix (310), wherein the resultant matrix comprises a weight for each of the plurality of attributes;
generating via the one or more hardware processors, a test case based on the generated resultant matrix and associated transpose thereof (312), wherein the generated test case comprises the one or more entities and corresponding one or more similar entities recommended for each of the one or more entities;
obtaining via the one or more hardware processors, a predicted result generated by a recommendation engine (314), wherein the predicted result comprises one or more recommended entities; and
performing via the one or more hardware processors, a comparison of (i) the generated test case and (ii) the predicted result to obtain an analytics report comprising at least one of accurate results and inaccurate results and to validate the recommendation engine and the predicted result based on the comparison (316).
2. The processor implemented method of claim 1, wherein the inter-relation
between the two or more attributes is derived based on a relative distance that is

directly proportional to similarity and ratio of the two or more attributes of the one or more entities.
3. The processor implemented method of claim 1, wherein the plurality of attributes comprised in the one or more dictionaries are arranged in an order based on an associated value thereof.
4. The processor implemented method of claim 1, further comprising generating a score for the accurate results, wherein the score is indicative of a qualitative validation of the recommendation engine.
5. The processor implemented method of claim 1, further comprising correcting the inaccurate results based on the comparison and providing at least one of corrected results and one or more observations to the recommendation engine for generating subsequent prediction results.
6. A system (100), comprising:
a memory (102) storing instructions;
one or more communication interfaces (106); and
one or more hardware processors (104) coupled to the memory (102) via the one or more communication interfaces (106), wherein the one or more hardware processors (104) are configured by the instructions to:
obtain an input comprising one or more entities;
generate one or more data dictionaries of a plurality of attributes specific to the one or more entities;
determine a relative weight for each of the plurality of attributes specific to the one or more entities, wherein the relative weight is a representation of inter-relation between two or more attributes of the plurality of attributes of each of the one or more entities;
compute a cumulative weight of the plurality of attributes based on the determined relative weight;

perform a one-hot encoding on the plurality of attributes based on the relative weight and the cumulative weight to generate a resultant matrix, wherein the resultant matrix comprises a weight for each of the plurality of attributes;
generate a test case based on the generated resultant matrix and associated transpose thereof, wherein the generated test case comprises the one or more entities and corresponding one or more similar entities recommended for each of the one or more entities;
obtain a predicted result generated by a recommendation engine, wherein the predicted result comprises one or more recommended entities; and
perform a comparison of (i) the generated test case and (ii) the predicted result to obtain an analytics report comprising at least one of accurate results and inaccurate results and to validate the recommendation engine and the predicted result based on the comparison.
7. The system of claim 6, wherein the inter-relation between the two or more attributes is derived based on a relative distance that is directly proportional to similarity and ratio of the two or more attributes of the one or more entities.
8. The system of claim 6, wherein the plurality of attributes comprised in the one or more dictionaries are arranged in an order based on an associated value thereof.
9. The system of claim 6, wherein the one or more hardware processors are further configured by the instructions to generate a score for the accurate results, wherein the score is indicative of a qualitative validation of the recommendation engine.
10. The system of claim 6, wherein the one or more hardware processors are further configured by the instructions to correct the inaccurate results based on the comparison and providing at least one of corrected results and one or more

observations to the recommendation engine for generating subsequent prediction results.