Abstract: A machine learning model is monitored by generating a time series of discrete time bins; for each of the discrete time bins: generating data point labels predicted using a labeling function to apply weak labels to incoming data; for each of the data point labels, generating one or more metric values based on one or more metrics by comparing the data point label to output labels of the machine learning model from the incoming data; and generating an aggregate metric for the time bin based on the one or more metric values for the data point labels of the time bin; and identifying anomalies in the aggregate metrics of the time bins of the time series.