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.

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.

Abstract: According to embodiments described in the specification, an exemplary method and a system is provided for matching electronic data records. A server maintains, in memory, a plurality of user profile records, each record including an identifier, one or more subject trait parameters, and one or more desired trait parameters. The server receives a query including a user profile record identifier associated with a first electronic device, determines a mutual match by searching the plurality of user profile records using the query to locate a matched user profile record identifier associated with a second electronic device, populates, on a display of the first electronic device, reduced profile information corresponding to the matched user profile record identifier, receives, from the first electronic device, input including a rating of the reduced profile information, adjusts the reduced profile information according to the input, and updates the display with the adjusted, reduced profile information.