Automatic machine learning-based processing with temporally inconsistent events

Abstract

Embodiments described herein reduce resource insufficiency of a resource source despite inconsistent resource accumulation at the resource source. For example, a request frequency may be determined to define times at which the resource source is predicted to be sufficient despite the inconsistent accumulation or influx. In one use case, with respect to a distributed computing environment having computing resource source(s)/pool(s), a requesting system may identify a machine learning model trained to generate predictions for a resource source at which inconsistent resource accumulation occurs. The system may obtain accumulation data that describes accumulation events at which resources were made available at the resource source. Using the accumulation data with the machine learning model, the system may determine a request frequency for a request type based on predicted times at which a threshold amount of resources is available at the resource source and may request resources in accordance with the request frequency.