IDENTIFYING ANOMALIES BASED ON CONTOURS DETERMINED THROUGH FALSE POSITIVES

Computer-implemented methods for identifying anomalies in a trained prediction model are provided. Aspects include receiving an input data set and obtaining a prediction from the trained prediction model based on the input data set. Aspects also include receiving, from a subject matter expert, a determination that the prediction is a false positive and creating a false positive contour based on the input data set. Aspects further include adding the false positive contour to a false positive feature space for the trained prediction model.