Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for automated detection of emergent behaviors in interactive agents of an interactive environment. The disclosed system represents an artificial intelligence based entity that utilizes a trained machine-learning-based clustering algorithm to group users together based on similarities in behavior. The clusters are processed based on a determination of the type of activity of the clustered users. In order to identify new categories of behavior and to label those new categories, a separate cluster analysis is performed using interaction data obtained at a subsequent time. The additional cluster analysis determines any change in behavior between the clustered sets and/or change in the number of users in a cluster. The identification of emergent user behavior enables the subject system to treat users differently based on their in-game behavior and to adapt in near real-time to changes in their behavior.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for automated real-time engagement in an interactive environment. The method includes extracting events from a stream of data received from a service provider system, the stream of data comprising event information of one or more real-life sporting events. The method also includes selecting a subset of the events, the subset of the events comprising events that are engaging to a user. The method also includes generating engagement events for an interactive environment based on the subset of the events, each of the engagement events replicating a scenario that corresponds to an event of one of the one or more real-life sporting events. The method also includes sending the engagement events to a client device.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for automated detection of emergent behaviors in interactive agents of an interactive environment. The disclosed system represents an artificial intelligence based entity that utilizes a trained machine-learning-based clustering algorithm to group users together based on similarities in behavior. The clusters are processed based on a determination of the type of activity of the clustered users. In order to identify new categories of behavior and to label those new categories, a separate cluster analysis is performed using interaction data obtained at a subsequent time. The additional cluster analysis determines any change in behavior between the clustered sets and/or change in the number of users in a cluster. The identification of emergent user behavior enables the subject system to treat users differently based on their in-game behavior and to adapt in near real-time to changes in their behavior.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for automated real-time engagement in an interactive environment. The disclosed system provides for producing a series of game challenges that replicate scenarios of a real-life event, and soliciting users to engage the series of game challenges to win an in-game reward. In some aspects, an extraction server engine obtains a live feed from a service provider of the real-life event and converts, on a periodic basis, the live feed into a parsed feed with a predetermined number of events. The extraction server engine then feeds its output to a trained neural network, which then selects a subset of the predetermined number of events. The trained neural network feeds the selections to a game server engine, which then feeds the selected events as in-game event challenges to a game client for presentation to an end user.