Abstract: The disclosed embodiments include computer-implemented systems and processes that train adaptively and deployment of coupled machine-learning and explainability processes within distributed computing environments. By way of example, an apparatus may receive first interaction data associated with a first temporal interval from a computing system. Based on an application of a first and a second trained artificial-intelligence process to an input dataset that includes at least a subset of the first interaction data, the apparatus may generate output data indicative of a predicted likelihood of an occurrence of a target event during a second temporal interval, and may generate explainability data that characterizes the predicted likelihood. The apparatus may also transmit portions the output and explainability data to the computing system, and the computing system may modify an operation of an executed application program in accordance with at least one the output or explainability data.

Abstract: To improve processing of the multi-event time-series data, information about each event type is aggregated for a group of time bins, such that an event bin embedding represents the occurring events of that type in the time bin. The event bin embedding may be based on an aggregated event value summarizing the values of that event type in the bin and a count of those events. The event bin embeddings across event types and time bins may be combined with an embedding for static data about the data instance and a representation token for input to an encoder. The encoder may apply an event-focused sublayer and a time-focused sublayer that attend to respective dimensions of the encoder. The model may be initially trained with self-supervised learning with time and event masking and then fine-tuned for particular applications.