Abstract: A system determines an amount of time available for responding to a request regarding eligibility for a client account for a modification based on a confidence grade for the client. The system transmits a first query and a second query. The system uses trained machine learning model(s) to determine respective estimated receipt times of first and second datasets responsive to the first and second queries, and to determine respective importance levels of the first and second datasets to determining the confidence grade. The system generates a preliminary confidence grade based on the first dataset, and delays generation of the confidence grade until the second dataset is received based on the estimated receipt times and importance levels. The system updates the preliminary confidence grade using the second dataset to generate the confidence grade, determines the eligibility determination, and updates the training of the machine learning models.

Abstract: In response to receipt of a request for an assessment of a user at a system and from a client terminal, the system identifies a duration of time available for responding to the request and starts a timer. The system transmits requests for information about the user to data sources. The system can and receive some responsive datasets back from the data sources, and can determine which responsive datasets are optimal to wait for and which are not based on how closely the timer is approaching the duration of time available for responding to the request. The system generates the assessment of the user based on the datasets that the system received before the timer reached a threshold time that is based on the duration of time available for responding to the request, and sends the assessment of the user to the client terminal.