# US 2021/0241334 A1 · Evaluation using similarity score for pairwise feature sets > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241334 A1 - Document ID: US20210241334A1 - Status: Published application - Kind: A1 - Application number: 16/777,246 - Filed: 2020-01-30 - Published: 2021-08-05 - Earliest claimed: 2020-01-30 - Assignees: Walmart Apollo, LLC - Applicants: Walmart Apollo, LLC - Inventors: Vidhya Rohini RAMAN; Paria GHORBANI - Web page: https://patentgrep.com/patent/US20210241334A1 ## CPC - G06Q 30/0609: {Qualifying participants for shopping transactions (payment transaction verification G06Q20/401)} - G06Q 30/0619: {Neutral agent} - G06Q 30/0641: {utilising user interfaces specially adapted for shopping} - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract Systems and methods of evaluating a third-party participant for inclusion in a networked environment are disclosed. A plurality of features representative of a third-party participant are received and at least one pairwise feature score is calculated for a first feature and a second feature selected from the plurality of features. The third-party participant is classified into one of a plurality of predetermined categories by a trained model based on the at least one pairwise feature score. ## Claims ### Claim 1 A system for generating item recommendations, comprising: a memory having instructions stored thereon, and a processor configured to read the instructions to: receive a plurality of features representative of a third-party participant; calculate at least one pairwise feature score for a first feature and a second feature selected from the plurality of features; classify the third-party participant into one of a plurality of predetermined categories by a trained model based on the at least one pairwise feature score; provide access to a network environment for the third-party participant based on a first classification of the third-party participant; and deny access to the network environment for the third-party participant based on a second classification of the third-party participant. ### Claim 2 (depends on 1) The system of claim 1, wherein the processor is configured to read the instructions to: calculate two or more pairwise comparisons for features included in the plurality of features; and calculate an ensemble score based on the two or more pairwise comparisons. ### Claim 3 (depends on 2) The system of claim 2, wherein the trained model classifies the third-party participant by comparing the ensemble score to at least one predetermined threshold. ### Claim 4 (depends on 1) The system of claim 1, wherein the trained model classifies the third-party participant by comparing the at least one pairwise feature score to a predetermined threshold. ### Claim 5 (depends on 1) The system of claim 1, wherein the at least one pairwise feature score is calculated as a Levenshtein distance between the first feature and the second feature. ### Claim 6 (depends on 1) The system of claim 1, wherein the plurality of predetermined categories includes an approved participant category and a rejected participant category. ### Claim 7 (depends on 1) The system of claim 1, wherein the trained model is generated using a model-based ranking of pairwise feature scores. ### Claim 8 (depends on 1) The system of claim 1, wherein the trained model is generated from a set of training data including a plurality of third-party participants each classified into one of the plurality of predetermined categories. ### Claim 9 A non-transitory computer readable medium having instructions stored thereon, wherein the instructions, when executed by a processor cause a device to perform operations comprising: receiving a plurality of features representative of a third-party participant; calculating at least one pairwise feature score for a first feature and a second feature selected from the plurality of features; classifying the third-party participant into one of a plurality of predetermined categories using a trained model based on the at least one pairwise feature score; provide access to a network environment for the third-party participant based on a first classification of the third-party participant; and deny access to the network environment for the third-party participant based on a second classification of the third-party participant. ### Claim 10 (depends on 9) The non-transitory computer-readable medium of claim 9, wherein the instructions, when executed by the processor cause the device to perform operations comprising: calculating two or more pairwise comparisons for features included in the plurality of features; and calculating an ensemble score based on the two or more pairwise comparisons. ### Claim 11 (depends on 10) The non-transitory computer-readable medium of claim 10, wherein the trained model classifies the third-party participant by comparing the ensemble score to at least one predetermined threshold. ### Claim 12 (depends on 9) The non-transitory computer-readable medium of claim 9, wherein the trained model classifies the third-party participant by comparing the at least one pairwise feature score to a predetermined threshold. ### Claim 13 (depends on 9) The non-transitory computer-readable medium of claim 9, wherein the at least one pairwise feature score is calculated as a Levenshtein distance between the first feature and the second feature. ### Claim 14 (depends on 9) The non-transitory computer-readable medium of claim 9, wherein the plurality of predetermined categories includes an approved seller category and a rejected seller category. ### Claim 15 (depends on 9) The non-transitory computer-readable medium of claim 9, wherein the trained model is generated using a model-based ranking of pairwise feature scores. ### Claim 16 A computer-implemented method of evaluating a third-party participant in a networked environment, comprising: receiving a plurality of features representative of a third-party participant; calculating at least one pairwise feature score for a first feature and a second feature selected from the plurality of features; classifying the third-party participant into one of a plurality of predetermined categories using a trained model based on the at least one pairwise feature score; provide access to a network environment for the third-party participant based on a first classification of the third-party participant; and deny access to the network environment for the third-party participant based on a second classification of the third-party participant. ### Claim 17 (depends on 16) The computer-implemented method of claim 16, comprising: calculating two or more pairwise comparisons for features included in the plurality of features; and calculating an ensemble score based on the two or more pairwise comparisons. ### Claim 18 (depends on 17) The computer-implemented method of claim 17, wherein the trained model classifies the third-party participant by comparing the ensemble score to at least one predetermined threshold. ### Claim 19 (depends on 16) The computer-implemented method of claim 16, wherein the trained model classifies the third-party participant by comparing the at least one pairwise feature score to a predetermined threshold. ### Claim 20 (depends on 16) The computer-implemented method of claim 16, wherein the at least one pairwise feature score is calculated as a Levenshtein distance between the first feature and the second feature.