# US 2017/0287044 A1 · Methods and Apparatus for Enhanced Product Recommendations > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2017/0287044 A1 - Document ID: US20170287044A1 - Status: Published application - Kind: A1 - Application number: 15/086,476 - Filed: 2016-03-31 - Published: 2017-10-05 - Earliest claimed: 2016-03-31 - Assignees: Under Armour, Inc. - Applicants: Under Armour, Inc. - Inventors: Madeline Taylor Rose; Patrick Howell; Joohyun Kim; Murtaza Ali; Sid Jitia; Chul Lee - Web page: https://patentgrep.com/patent/US20170287044A1 ## CPC - G06Q 30/0631: {Recommending goods or services} - H04L 67/306: User profiles - 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 - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Apparatus and methods are given for providing enhanced product recommendations. In one embodiment, products are recommended to a consumer based on information manually entered by the consumer and/or derived from data relating to the consumer obtained from a health-monitoring platform. The recommended products are provided from a recommendation engine to a human operator or curator at an item selection entity, the curator selects a predetermined number of the recommended products for delivery to the consumer. Such delivery is established by the consumer to occur periodically (such as monthly) as part of a subscription service. Product recommendations are adjusted over time to relate to customer activity and interest data accumulated from the health-monitoring platform. In one embodiment, a recommendation engine is configured to specifically tailor its recommendation algorithms based on feedback information received from the curator and/or the consumer. ## Claims ### Claim 1 A method of enabling product recommendations, said method comprising: receiving a plurality of product records and a plurality of user profiles, each of said plurality of product records and each of said plurality of user profiles comprising one or more aspects; applying a comparison algorithm to said one or more aspects of an individual one of said user profiles and said one or more aspects of each of said plurality of product records to identify a subset thereof which exhibit a threshold level of similarity; providing said identified subset of said plurality of product records to a selection entity, said selection entity configured to select first products from said identified subset for delivery to a consumer; utilizing information received from said selection entity which identifies second ones of said identified subset which were not selected to adjust one or more first factors of said comparison algorithm; and utilizing information received from a product warehouse which identifies one or more of said first products which were delivered to said customer and subsequently returned to adjust one or more second factors of said comparison algorithm. ### Claim 2 (depends on 1) The method of claim 1, wherein said one or more first factors of said comparison algorithm comprise at least one of: said threshold, said comparison algorithm, said one or more aspects of said individual one of said user profiles, and/or said one or more aspects of said second ones of said identified subset. ### Claim 3 (depends on 1) The method of claim 1, wherein said one or more second factors of said comparison algorithm comprise at least one of: said threshold, said comparison algorithm, said one or more aspects of said individual one of said user profiles, and/or said one or more aspects of said second ones of said identified subset. ### Claim 4 (depends on 1) The method of claim 1, wherein said one or more aspects of said plurality of product records comprise at least one of: a product name, a product type, a product gender, a product size availability, a sports category, and an activity level. ### Claim 5 (depends on 1) The method of claim 1, wherein said one or more aspects of said plurality of user profiles comprise at least one of: a user identifier, a user gender, a user size, a sports category, and an activity level. ### Claim 6 (depends on 1) The method of claim 1, wherein each of said plurality of product records comprises a vector including said one or more aspects and each of said plurality of user profiles comprises a vector including a same number of said one or more aspects as said vectors of said plurality of product records. ### Claim 7 (depends on 6) The method of claim 6, wherein said comparison algorithm comprises calculating a dot product of a particular one of said plurality of user profiles and each of said product records to produce a scalar quantity, and comparing said scalar quantity to said threshold value. ### Claim 8 (depends on 1) The method of claim 1, wherein said first products are delivered to said consumer periodically as a subscription-based service and without further input from said consumer. ### Claim 9 A method of enabling product recommendations, said method comprising: generating a plurality product records representative of a respective plurality of products for purchase, each of said product records comprising a number of descriptive aspects; obtaining consumer profile data relating to an individual consumer; converting said consumer profile data into a consumer profile record comprising a number of descriptive aspects; utilizing one or more of said descriptive aspects of said consumer profile to filter out a subset of said plurality of product records; identifying, via a comparison of said consumer profile record against each of a subset of said plurality of product profile records which were not filtered out, one or more products which meet a threshold level of similarity to said consumer profile data; providing a list of said identified one or more products to a human operator; enabling said human operator to select from said list individual ones of said identified one or more products; generating a delivery order of said selected individual ones of said identified one or more products for delivery to said consumer; and adjusting at least one factor of said comparison based on said human operator selections. ### Claim 10 (depends on 9) The method of claim 9, further comprising providing said delivery order to a product warehouse, said product warehouse causing said identified one or more products to be delivered to said consumer. ### Claim 11 (depends on 10) The method of claim 10, further comprising: receiving, from said product warehouse, information relating to a return of certain ones of said products delivered thereto; and adjusting at least one second factor of said comparison based on said return of said certain ones of said products delivered to said consumer. ### Claim 12 (depends on 11) The method of claim 11, wherein said information relating to a return further comprises descriptive information entered by said consumer relating to a reason for said return; wherein said act of adjusting said at least one second factor of said comparison is based on said descriptive information. ### Claim 13 (depends on 9) The method of claim 9, wherein said consumer profile data is obtained from at least one social media-enabled application via network communication thereto. ### Claim 14 (depends on 13) The method of claim 13, further comprising periodically updating said consumer profile data according to social media posts and/or changes made by said consumer. ### Claim 15 (depends on 9) The method of claim 9, further comprising enabling said human operator to enter descriptive information related to individual ones of said identified one or more products which were not selected; wherein said act of adjusting said at least one factor of said comparison is based on said descriptive information. ### Claim 16 An apparatus configured to provide product recommendations, said apparatus comprising: at least one network interface configured to receive a plurality of product records and a user profile; a storage apparatus; and a processor configured to execute at least one computer program, said computer program comprising a plurality of instructions which are configured to, when executed by said processor, cause said apparatus to: apply a comparison algorithm to one or more aspects of said user profile and one or more aspects of each of said plurality of product records to identify a subset thereof which exhibit a threshold level of similarity to said user profile; provide said subset of said plurality of product records as a selectable list to a human operator via said interface, selection of individual ones of said selectable list by said human operator causing: generation of feedback information regarding whether each of said subset was selected or not selected by said human operator; and generation of a delivery order for delivery of products associated with said selected individual ones of said selectable list to a user associated to said user profile; and utilize said feedback information to adjust one or more factors of said comparison algorithm. ### Claim 17 (depends on 16) The apparatus of claim 16, wherein said user profile is obtained from at least one social media-enabled application and said plurality of instructions are further configured to, when executed by said processor, cause said apparatus to convert said user profile into a same format as said plurality of product records. ### Claim 18 (depends on 16) The apparatus of claim 16, wherein said adjustment of said one or more factors of said comparison algorithm comprises adjustment of at least one of: said threshold, said comparison algorithm, said one or more aspects of said user profile, and/or said one or more aspects of said subset of said plurality of product records. ### Claim 19 (depends on 16) The apparatus of claim 16, wherein said delivery of said products associated with said selected individual ones of said selectable list occurs periodically as a subscription-based service and without further input from said user. ### Claim 20 (depends on 16) The apparatus of claim 16, said plurality of instructions are further configured to, when executed by said processor, cause said apparatus to: provide said delivery order to a product warehouse, said product warehouse causing said products associated with said selected individual ones of said selectable list to be delivered to said user; receive, from said product warehouse, information relating to a return of certain ones of said products delivered to said user; and adjusting at least one second factor of said comparison based on said return.