# US 2019/0378374 A1 · Systems and methods for generating multidimensional data structures based on fantasy sports account activity > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0378374 A1 - Document ID: US20190378374A1 - Status: Published application - Kind: A1 - Application number: 16/437,782 - Filed: 2019-06-11 - Published: 2019-12-12 - Earliest claimed: 2018-06-11 - Assignees: DraftKings, Inc. - Applicants: DraftKings, Inc. - Inventors: Rick Sawyer; Jordan Mendell; Frank Lo; Alexander John Krusz; Brendan Thompson Grove - Web page: https://patentgrep.com/patent/US20190378374A1 ## CPC - G07F 17/3237: {about the players, e.g. profiling, responsible gaming, strategy/behavior of players, location of players} - G06F 16/24578: {using ranking} - G06F 16/285: {Clustering or classification} - G06F 16/3347: {using vector based model} - G06F 16/35: Clustering; Classification - G06F 16/9535: Search customisation based on user profiles and personalisation - G07F 17/3211: {Display means} - G07F 17/3244: {Payment aspects of a gaming system, e.g. payment schemes, setting payout ratio, bonus or consolation prizes} - G07F 17/3209: {Input means, e.g. buttons, touch screen} - G07F: COIN-FREED OR LIKE APPARATUS (coin sorting G07D3/00; coin testing G07D5/00; {handling coins or paper currencies apart from payment activated apparatus G07D; payment architectures, schemes or protocols G06Q20/00}) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Systems and methods for generating a multidimensional data structure based on fantasy sports account activity are described herein. Processors can maintain user profiles, each user profile having player lineups associated with fantasy sports contests. The processors can identify, for a first user profile, player lineups of the first user profile and respective contests for which the player lineups were entered. Each player lineup including players having players attributes. Each contest having contest attributes. The processors can generate, for the first user profile, a multidimensional data structure including a plurality of features. Each feature can have a respective value that is based on the player attributes corresponding to the players included in the player lineups and the contest attributes corresponding to the contests for which the player lineups were entered. The processors can then provide content selected using the generated multidimensional data structure to a device associated with the user profile. ## Claims ### Claim 1 A method for generating a multidimensional data structure using fantasy sports account activity, comprising: maintaining, by one or more processors, a plurality of user profiles, each of the user profiles having one or more player lineups associated with at least one fantasy sports contest; identifying, by the one or more processors, for a first user profile of the plurality of user profiles, one or more player lineups of the first user profile and one or more respective contests for which the player lineups were entered, each of the player lineups including a plurality of players, each of the plurality of players having one or more players attributes, each of the contests having one or more contest attributes; generating, by the one or more processors, for the first user profile, a multidimensional data structure including a plurality of features, each feature having a respective value that is based on the player attributes corresponding to the players included in the one or more player lineups and the contest attributes corresponding to the one or more respective contests for which the player lineups were entered; selecting, by the one or more processors using the multidimensional data structure, content for presentation to a device associated with the user profile, the content selected using an association between at least one player attribute and at least one contest attribute identified by the multidimensional data structure; and providing, by the one or more processors, using the generated multidimensional data structure, the content to the device associated with the user profile. ### Claim 2 (depends on 1) The method of claim 1, wherein the one or more player attributes include one or more of the following: a name, a sport category, a location, a team value, a position value, a price parameter and one or more future contests specific to the respective player. ### Claim 3 (depends on 1) The method of claim 1, wherein the one or more contest attributes include one or more of the following: a sport category, a price parameter, a prize parameter, a registrant threshold, a registrant limit, a current registrant count, a day value, a time value, a duration value, a contest type, and an experience level. ### Claim 4 (depends on 1) The method of claim 1, wherein each user profile in the plurality of user profiles includes data corresponding to user interactions with one or more fantasy sports contests executing on a device associated with the respective user. ### Claim 5 (depends on 1) The method of claim 1, comprising: determining a user type for each user profile in the plurality of user profiles based on a frequency of use; and determining a skill level for each user profile in the plurality of user profiles based on an outcome value corresponding to one or more fantasy sports contests the respective user participated in. ### Claim 6 (depends on 1) The method of claim 1, comprising: generating an activity profile for each user profile having data associated with one or more fantasy sports contests the respective user participated in; modifying the multidimensional data structure responsive to the activity profile of the first user profile; and selecting subsequent content for the first user profile based on the modification to the multidimensional data structure. ### Claim 7 (depends on 6) The method of claim 6, comprising updating a second user profile based on the activity profile of the first user profile. ### Claim 8 (depends on 1) The method of claim 1, comprising generating, using a clustering algorithm, a user cluster based on a plurality of multidimensional data structures corresponding to the plurality of user profiles, wherein each user profile in the user cluster having multiple player attributes in common and multiple contest attributes in common. ### Claim 9 (depends on 1) The method of claim 1, comprising: receiving, by the one or more processors, one or more contest attributes data from a third party server; and determining, by the one or more processors using the multidimensional data structure, the association between the at least player attribute and the at least one contest attributes using the one or more contest attributes from the third party server. ### Claim 10 (depends on 1) The method of claim 1, comprising: determining, by the one or more processors, a profile association between the user profile and the multidimensional data structure; and storing, by the one or more processors, the profile association in the user profile. ### Claim 11 (depends on 1) The method of claim 1, comprising: modifying, by the one or more processors, at least one player attribute or at least one contest attribute associated with the user profile using a user behavior metric from the one or more respective contests for which the player lineups were previously entered; and generating, by the one or more processors, one or more features of the plurality of features to include the at least one modified player attribute or the at least one modified contest attribute. ### Claim 12 A system for generating a multidimensional data structure using fantasy sports account activity, comprising: one or more processors; and memory comprising; computer-readable instructions stored in memory that, when executed by the one or more processors, cause the one or more processors to: maintain a plurality of user profiles, each of the user profiles having one or more player lineups associated with at least one fantasy sports contest; identify, for a first user profile of the plurality of user profiles, one or more player lineups of the first user profile and one or more respective contests for which the player lineups were entered, each of the player lineups including a plurality of players, each of the plurality of players having one or more players attributes, each of the contests having one or more contest attributes; generate, for the first user profile, a multidimensional data structure including a plurality of features, each feature having a respective value that is based on the player attributes corresponding to the players included in the one or more player lineups and the contest attributes corresponding to the one or more respective contests for which the player lineups were entered; select, using the multidimensional data structure, content for presentation to a device associated with the user profile, the content selected using an association between at least one player attribute and at least one contest attribute identified by the multidimensional data structure; and provide, using the generated multidimensional data structure, the content to the device associated with the user profile. ### Claim 13 (depends on 12) The system of claim 12, wherein the one or more player attributes include one or more of the following: a name, a sport category, a location, a team value, a position value, a price parameter and one or more future contests specific to the respective player; and the one or more contest attributes include one or more of the following: a sport category, a price parameter, a prize parameter, a registrant threshold, a registrant limit, a current registrant count, a day value, a time value, a duration value, a contest type, and an experience level. ### Claim 14 (depends on 12) The system of claim 12, wherein the computer-readable instructions, when executed by the processor, further cause the one or more processors to: determine a user type for each user profile in the plurality of user profiles based on a frequency of use; and determine a skill level for each user profile in the plurality of user profiles based on an outcome value corresponding to one or more fantasy sports contests the respective user participated in. ### Claim 15 (depends on 12) The system of claim 12, wherein the computer-readable instructions, when executed by the processor, further cause the one or more processors to: generate an activity profile for each user profile having data associated with one or more fantasy sports contests the respective user participated in; modify the multidimensional data structure responsive to the activity profile of the first user profile; and select subsequent content for the first user profile based on the modification to the multidimensional data structure. ### Claim 16 (depends on 15) The system of claim 15, wherein the computer-readable instructions, when executed by the processor, further cause the one or more processors to: update a second user profile based on the activity profile of the first user profile. ### Claim 17 (depends on 12) The system of claim 12, wherein the computer-readable instructions, when executed by the processor, further cause the one or more processors to: generate, using a clustering algorithm, a user cluster based on a plurality of multidimensional data structures corresponding to the plurality of user profiles, wherein each user profile in the user cluster having multiple player attributes in common and multiple contest attributes in common. ### Claim 18 (depends on 12) The system of claim 12, wherein the computer-readable instructions, when executed by the processor, further cause the one or more processors to: receive, by the one or more processors, one or more contest attributes data from a third party server; and determine, by the one or more processors using the multidimensional data structure, the association between the at least player attribute and the at least one contest attributes using the one or more contest attributes from the third party server. ### Claim 19 (depends on 12) The system of claim 12, wherein the computer-readable instructions, when executed by the processor, further cause the one or more processors to: determine a profile association between the user profile and the multidimensional data structure; and store the profile association in the user profile. ### Claim 20 (depends on 12) The system of claim 12, wherein the computer-readable instructions, when executed by the processor, further cause the one or more processors to: modify at least one player attribute or at least one contest attribute associated with the user profile using a user behavior metric from the one or more respective contests for which the player lineups were previously entered; and generate one or more features of the plurality of features to include the at least one modified player attribute or the at least one modified contest attribute.