Dynamic difficulty adjustment
Embodiments of systems presented herein may perform automatic granular difficulty adjustment. In some embodiments, the difficulty adjustment is undetectable by a user. Further, embodiments of systems disclosed herein can review historical user activity data with respect to one or more video games to generate a game retention prediction model that predicts an indication of an expected duration of game play. The game retention prediction model may be applied to a user's activity data to determine an indication of the user's expected duration of game play. Based on the determined expected duration of game play, the difficulty level of the video game may be automatically adjusted.
1. A computer-implemented method comprising:
as implemented by an interactive computing system configured with specific computer-executable instructions,
accessing user interaction data of a user, wherein the user interaction data is associated with interaction by the user with a video game;
accessing a plurality of cluster definitions associated with a plurality of clusters, wherein each cluster definition of the plurality of cluster definitions is associated with a different cluster of the plurality of clusters, and wherein each cluster of the plurality of clusters comprises an identity of one or more users who share one or more engagement characteristics associated with interaction with the video game;
selecting a target cluster from the plurality of clusters based at least in part on the user interaction data of the user and the plurality of cluster definitions;
identifying a configuration value for a state variable of the video game based at least in part on the target cluster; and
configuring the state variable using the configuration value, wherein configuring the state variable adjusts a difficulty of the video game.
2. The computer-implemented method of claim 1 , wherein the state variable comprises a seed value that modifies execution of the video game.
3. The computer-implemented method of claim 1 , further comprising monitoring the user's interaction with the video game over a time period to obtain the user interaction data.
4. The computer-implemented method of claim 1 , wherein a change in execution of the video game associated with configuring the state variable is undetectable by the user.
5. The computer-implemented method of claim 1 , wherein selecting the target cluster from the plurality of clusters comprises matching characteristics of the user interaction data with characteristics associated with each of the plurality of clusters.
6. The computer-implemented method of claim 1 , further comprising storing an association between the user and the target cluster.
7. The computer-implemented method of claim 1 , wherein the plurality of clusters are associated with the video game, and wherein a second plurality of clusters are associated with a second video game.
8. The computer-implemented method of claim 1 , wherein each cluster from the plurality of clusters is associated with a different difficulty level for the video game, and wherein identifying the configuration value for the state variable comprises determining a difficulty level associated with the target cluster.
9. The computer-implemented method of claim 1 , further comprising:
determining a user success value by predicting a user's success at playing the video game based at least in part on the target cluster and the user interaction data; and
selecting the configuration value based at least in part on the user success value.
10. The computer-implemented method of claim 1 , further comprising:
obtaining second user interaction data of the user based on interaction with the video game that is more recent than the interaction with the video game associated with the user interaction data; and
modifying the configuration value for the state variable based at least in part on the second user interaction data.
11. The computer-implemented method of claim 1 , wherein the one or more engagement characteristics may correspond to one or more of time played, success rate with respect to in-game objectives, or difficulty of video games.
12. The computer-implemented method of claim 1 , further comprising presenting an engagement characteristic associated with the target cluster to the user.
13. The computer-implemented method of claim 12 , further comprising receiving feedback from the user associated with the engagement characteristic and modifying selection of the target cluster to select a second target cluster based at least in part on the feedback from the user.
14. A system comprising:
an electronic data store configured to store cluster definitions that group user identities of users who play a video game, wherein each cluster definition is associated with a particular engagement characteristic associated with playing the video game; and
a hardware processor in communication with the electronic data store, the hardware processor configured to execute specific computer-executable instructions to at least:
access user interaction data of a user, wherein the user interaction data is associated with interaction by the user with the video game;
access from the electronic data store a plurality of cluster definitions associated with a plurality of clusters, wherein each cluster definition of the plurality of cluster definitions is associated with a different cluster of the plurality of clusters, and wherein each cluster of the plurality of clusters comprises an identity of one or more users who share one or more engagement characteristics associated with interaction with the video game;
select a target cluster from the plurality of clusters based at least in part on the user interaction data of the user and the plurality of cluster definitions;
identify a configuration value for a state variable of the video game based at least in part on the target cluster; and
configure the state variable using the configuration value, wherein configuring the state variable adjusts a difficulty of the video game.
15. The system of claim 14 , wherein a change in execution of the video game associated with configuring the state variable is undetectable by the user.
16. The system of claim 14 , wherein the hardware processor is further configured to select the target cluster from the plurality of clusters by at least matching characteristics of the user interaction data with characteristics associated with each of the plurality of clusters.
17. The system of claim 14 , wherein each cluster from the plurality of clusters is associated with a different difficulty level for the video game, and wherein the hardware processor is further configured to identify the configuration value for the state variable by at least determining a difficulty level associated with the target cluster.
18. The system of claim 14 , wherein the hardware processor is further configured to execute specific computer-executable instructions to at least:
determine a predicted success of the user at playing the video game based at least in part on the target cluster and the user interaction data; and
select the configuration value based at least in part on the predicted success.
19. The system of claim 14 , wherein the hardware processor is further configured to execute specific computer-executable instructions to at least:
obtain second user interaction data of the user based on interaction with the video game that is more recent than the interaction with the video game associated with the user interaction data; and
modify the configuration value for the state variable based at least in part on the second user interaction data.
20. The system of claim 14 , wherein the hardware processor is further configured to execute specific computer-executable instructions to at least:
present an engagement characteristic associated with the target cluster to the user;
receive feedback from the user associated with the engagement characteristic; and
modify selection of the target cluster to select a second target cluster based at least in part on the feedback from the user.