DATA QUALITY MODEL FOR DRIFT-RESISTANT INFERENCES

Abstract

A method and related system for accounting for error drift in a machine learning model includes determining a first anomalous sequence in a first data stream by using a data quality model, providing the first data stream to a first decision model in lieu of a second decision model based on the first anomalous sequence, and determining a set of patterns based on the first anomalous sequence. The method further includes generating a set of synthetic sequences derived from the set of patterns, updating the data quality model based on the set of synthetic sequences.

CPC Classifications