# US 12,182,847 B2 · Method and apparatus for providing recommendations based on return data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,182,847 B2 - Document ID: US12182847B2 - Status: Granted - Kind: B2 - Application number: 17/684,017 - Filed: 2022-03-01 - Published: 2023-09-07 - Granted: 2024-12-31 - Earliest claimed: 2022-03-01 - Assignees: Affirm, Inc. - Applicants: Affirm, Inc. - Inventors: Enric Gili Fort; Hossein Ghodrati Noushahr; Pablo Vargas Ibarra; Mark L. Sainz Zaragoza; Eduardo Vilar - Web page: https://patentgrep.com/patent/US12182847B2 ## CPC - G06Q 30/01: Customer relationship services - G06Q 30/0631: {Recommending goods or services} - G06Q 30/0202: Market predictions or forecasting for commercial activities - G06Q 30/0282: Rating or review of business operators or products - G06Q 30/0283: Price estimation or determination - G06Q 30/0601: Electronic shopping [e-shopping] - G06Q 30/0643: {graphically representing goods, e.g. 3D product representation} - 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 A method of recommending products in association with product returns may include receiving a return request from a customer associated with a returned product and receiving search results based on a search for relevant products to the returned product. The method may further include filtering the search results based on a likelihood of return rating of at least some of the relevant products, and displaying a plurality of recommended products based on the filtering of the search results. ## Claims ### Claim 1 An apparatus for recommending products in association with product returns, the apparatus comprising processing circuitry configured to: receive a return request from a customer associated with a returned product from a given merchant; receive search results based on a search for relevant products to the returned product; filter the search results based on a likelihood of return rating of at least some of the relevant products, the likelihood of return rating being determined based on a return model generated based on associations made with respect to return volume, return frequency and repurchase frequency associated with the given merchant, the customer and the returned product; modify ordering of the search results and apply exclusions to the search results; display a plurality of recommended products based on the modified ordering of the search results and the application of exclusions to the search results; receive feedback regarding performance of the return model and merchant applied tags associating products with exclusion and ordering adjustment instructions; and update the return model based on the feedback received and the merchant applied tags, wherein modifying ordering of the search results and applying exclusions to the search results comprises preventing display of at least one selected product from the search results responsive to one of the merchant applied tags identifying the at least one selected product for exclusion from display and adjusting an ordering of at least another selected product from the search results responsive to another of the merchant applied tags identifying the at least another selected product with a positive or negative association. ### Claim 2 (depends on 1) The apparatus of claim 1, wherein the processing circuitry is further configured to: receive return data relating to product returns for a plurality of products; determine a return frequency dataset including likelihood of return ratings for the products based on comparing sales volume to return volume for each of the products. ### Claim 3 (depends on 1) The apparatus of claim 1, wherein filtering the search results comprises preventing display of a selected product from the search results responsive to the selected product having a corresponding likelihood of return rating below a threshold value. ### Claim 4 (depends on 1) The apparatus of claim 1, wherein the returned product is provided by a vendor, and wherein the related products are limited only to products offered by the vendor. ### Claim 5 (depends on 1) The apparatus of claim 1, wherein displaying the plurality of recommended products comprises displaying a modified price for each of the recommended products, the modified price being a regular price of each respective one of the recommended products minus a return value of the returned product. ### Claim 6 (depends on 5) The apparatus of claim 5, wherein displaying the plurality of recommended products comprises displaying each product with an indication of the regular price, and an indication of the modified price proximate to each other. ### Claim 7 (depends on 1) The apparatus of claim 1, wherein displaying the plurality of recommended products comprises displaying the plurality of recommended products on each of a plurality of separate points along a product return process flow path. ### Claim 8 (depends on 7) The apparatus of claim 7, wherein a different group of products is displayed at each of the separate points. ### Claim 9 (depends on 1) The apparatus of claim 1, wherein filtering the search results further comprises removing any product previously returned by the customer from the search results. ### Claim 10 (depends on 1) The apparatus of claim 1, wherein updating the return model comprises updating the return model in real time. ### Claim 11 A method of recommending products in association with product returns, the method comprising: receiving a return request from a customer associated with a returned product from a given merchant; receiving search results based on a search for relevant products to the returned product; filtering the search results based on a likelihood of return rating of at least some of the relevant products, the likelihood of return rating being determined based on a return model generated based on associations made with respect to return volume, return frequency and repurchase frequency associated with the given merchant, the customer and the returned product; modifying ordering of the search results and applying exclusions to the search results; displaying a plurality of recommended products based on the modified ordering of the search results and the application of exclusions to the search results; receiving feedback regarding performance of the return model and merchant applied tags associating products with exclusion and ordering adjustment instructions; and updating the return model based on the feedback received and the merchant applied tags, wherein displaying the plurality of recommended products comprises displaying the plurality of recommended products on each of a plurality of separate points along a product return process flow path, and wherein modifying ordering of the search results and applying exclusions to the search results comprises preventing display of at least one selected product from the search results responsive to one of the merchant applied tags identifying the at least one selected product for exclusion from display and adjusting an ordering of at least another selected product from the search results responsive to another of the merchant applied tags identifying the at least another selected product with a positive or negative association. ### Claim 12 (depends on 11) The method of claim 11, further comprising: receiving return data relating to product returns for a plurality of products; determining a return frequency dataset including likelihood of return ratings for the products based on comparing sales volume to return volume for each of the products. ### Claim 13 (depends on 11) The method of claim 11, wherein filtering the search results comprises preventing display of a selected product from the search results responsive to the selected product having a corresponding likelihood of return rating below a threshold value. ### Claim 14 (depends on 11) The method of claim 11, wherein the returned product is provided by a vendor, and wherein the related products are limited only to products offered by the vendor. ### Claim 15 (depends on 11) The method of claim 11, wherein displaying the plurality of recommended products comprises displaying a modified price for each of the recommended products, the modified price being a regular price of each respective one of the recommended products minus a return value of the returned product. ### Claim 16 (depends on 15) The method of claim 15, wherein displaying the plurality of recommended products comprises displaying each product with an indication of the regular price, and an indication of the modified price proximate to each other. ### Claim 17 (depends on 11) The method of claim 11, wherein a different group of products is displayed at each of the separate points. ### Claim 18 (depends on 11) The method of claim 11, wherein filtering the search results further comprises removing any product previously returned by the customer from the search results. ### Claim 19 (depends on 11) The method of claim 11, wherein updating the return model comprises updating the return model in real time.