# US 2017/0286977 A1 · Consumption based subscription frequency recommendations > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2017/0286977 A1 - Document ID: US20170286977A1 - Status: Published application - Kind: A1 - Application number: 15/494,409 - Filed: 2017-04-21 - Published: 2017-10-05 - Earliest claimed: 2012-03-14 - Assignees: Amazon Technologies, Inc. - Applicants: Amazon Technologies, Inc. - Inventors: James Gregory Allen; Jason E. Dishlip; Steven F. Toth; Ming-Hsiu Wang; Michael J. Beenen; Laura E. Ford; Kevin Alexander Lee - Web page: https://patentgrep.com/patent/US20170286977A1 ## CPC - G06Q 30/0259: {based on store location} - G06Q 30/0254: {based on statistics} - G06Q 30/0201: Market modelling; Market analysis; Collecting market data - G06Q 30/0264: {based upon schedule} - 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 Disclosed herein are systems, methods, and non-transitory computer-readable storage media for consumption based subscription frequency recommendations. A system configured to practice the example method first evaluates purchase statistics for an item to determine a consumption frequency. The system receives from a user a request for the item, and presents to the user a subscription recommendation based on the consumption frequency. The system can also provide recommendations for accessories by evaluating purchase statistics for an item to determine an accessory for the item, wherein a number of times the accessory is purchased with the item exceeds a threshold, receiving from a user a request for a subscription for recurring purchases of the item, and presenting to the user a recommendation to include the accessory as part of the subscription. ## Claims ### Claim 1 A system comprising: at least one processor; and a non-transitory computer-readable storage medium having stored therein instructions the instructions, when executed by the at least one processor, cause the at least one processor to: identify a subscription for recurring purchases of a first item associated with a plurality of customer profiles, a customer profile comprises one or more customer attributes that indicate demographic information and regional information; detect an event associated with a first customer based at least on a purchase of a second item different than the first item; determine a similarity vector between one or more of the plurality of customer profiles for customers that purchased the second item, the similarity vector includes a weight for at least one customer attribute having a common occurrence in the one or more of the plurality of customer profiles; determine a modified customer attribute for a first customer profile associated with the first customer based at least on the similarity vector; and modify, based at least on the modified customer attribute, a first subscription for recurring purchases of the first item that is associated with the first customer profile. ### Claim 2 (depends on 1) The system of claim 1, wherein the instructions to modify the first subscription further cause the at least one processor to change at least one of a subscription frequency or the first item. ### Claim 3 (depends on 1) The system of claim 1, wherein the instructions, when executed, further cause the at least one processor to: notify the first customer regarding changes to the first subscription. ### Claim 4 (depends on 1) The system of claim 1, wherein the instructions, when executed, further cause the at least one processor to: track an acceptance rate for modifications to the subscription for respective customer profiles, and wherein the instructions to determine the modified customer attribute further cause the at least one processor to determine the modified customer attribute based at least in part on the acceptance rate. ### Claim 5 (depends on 1) The system of claim 1, wherein the instructions, when executed, further cause the at least one processor to: determine the second item is an accessory for the first item based at least in part on the event. ### Claim 6 (depends on 1) The system of claim 1, wherein the instructions to identify the subscription further cause the at least one processor to identify the subscription for recurring purchases of the first item based at least in part on consumption patterns associated with the plurality of customer profiles. ### Claim 7 A non-transitory computer-readable storage medium having stored therein instructions, the instructions, when executed by at least one computing device, cause the at least one computing device to: identify a subscription for recurring purchases of a first item associated with a plurality of customer profiles, a customer profile comprises one or more customer attributes that indicate demographic information and regional information; detect an event associated with a first customer based at least on a purchase of a second item different than the first item; determine a similarity vector between one or more of the plurality of customer profiles associated with customers that purchased the second item, the similarity vector includes a weight for at least one customer attribute having a common occurrence in the one or more of the plurality of customer profiles; determine a modified customer attribute for a first customer profile associated with the first customer based at least on the similarity vector; and modify a first subscription associated with the first customer profile, for recurring purchases of the first item, based at least on the modified customer attribute. ### Claim 8 (depends on 7) The non-transitory computer-readable storage medium of claim 7, wherein the instructions to modify the first subscription further cause the at least one computing device to change at least one of a subscription frequency or the first item. ### Claim 9 (depends on 7) The non-transitory computer-readable storage medium of claim 7, wherein the instructions, when executed, further cause the at least one computing device to: notify the first customer regarding changes to the first subscription. ### Claim 10 (depends on 7) The non-transitory computer-readable storage medium of claim 7, wherein the instructions, when executed, further cause the at least one computing device to: track an acceptance rate for modifications to the subscription for respective customer profiles, and wherein the instructions to determine the modified customer attribute further cause the at least one computing device to determine the modified customer attribute based at least in part on the acceptance rate. ### Claim 11 (depends on 7) The non-transitory computer-readable storage medium of claim 7, wherein the instructions, when executed, further cause the at least one computing device to: determine the second item is an accessory for the first item based at least in part on the event. ### Claim 12 (depends on 7) The non-transitory computer-readable storage medium of claim 7, wherein the instructions to identify the subscription further cause the at least one computing device to identify the subscription for recurring purchases of the first item based at least in part on consumption patterns associated with the plurality of customer profiles. ### Claim 13 A method comprising: identifying a subscription for recurring purchases of a first item associated with a plurality of customer profiles, a customer profile comprises one or more customer attributes that indicate demographic information and regional information; detecting an event associated with a first customer based at least on a purchase of a second item different than the first item; determining a similarity vector between one or more of the plurality of customer profiles associated with customers that purchased the second item, the similarity vector includes a weight for at least one customer attribute having a common occurrence in the one or more of the plurality of customer profiles; determining a modified customer attribute for a first customer profile associated with the first customer based at least on the similarity vector; and modifying a first subscription associated with the first customer profile, for recurring purchases of the first item, based at least on the modified customer attribute. ### Claim 14 (depends on 13) The method of claim 13, wherein modifying the first subscription further comprises changing at least one of a subscription frequency or the first item. ### Claim 15 (depends on 13) The method of claim 13, further comprising: notifying the first customer regarding changes to the first subscription. ### Claim 16 (depends on 13) The method of claim 13, further comprising: tracking an acceptance rate for modifications to the subscription for respective customer profiles, and wherein determining the modified customer attribute further comprises determining the modified customer attribute based at least in part on the acceptance rate. ### Claim 17 (depends on 13) The method of claim 13, further comprising: determining the second item is an accessory for the first item based at least in part on the event. ### Claim 18 (depends on 13) The method of claim 13, wherein identifying the subscription further comprises identifying the subscription for recurring purchases of the first item based at least in part on consumption patterns associated with the plurality of customer profiles.