Microsoft Technology Licensing, LLC

Shilpa Gupta

Shaunak Chatterjee

Yang Yang

Aastha Jain

Zheng Li

Romer E Rosales

Souvik Ghosh

Boyi Chen

Myunghwan Kim

Yanbin Jiang

Hema Raghavan

Kexin Nie

Technologies for monitoring performance of a machine learning model include receiving, by an unsupervised anomaly detection function, digital time series data for a feature metric; where the feature metric is computed for a feature that is extracted from an online system over a time interval; where the machine learning model is to produce model output that relates to one or more users' use of the online system; using the unsupervised anomaly detection function, detecting anomalies in the digital time series data; labeling a subset of the detected anomalies in response to a deviation of a time-series prediction model from a predicted baseline model exceeding a predicted deviation criterion; creating digital output that identifies the feature as associated with the labeled subset of the detected anomalies; causing, in response to the digital output, a modification of the machine learning model.

Machine learning model monitoring

A system, a machine-readable storage medium storing instructions, and a computer-implemented method are described herein are directed to Future Connection Engine that generates a select pairing of member accounts for a potential social network connection. The Future Connection Engine predicts, according to the prediction model, a first number of subsequent social network connections for a first member account in the select pairing that will occur after establishing the potential social network connection and a second number of subsequent social network connections for a second member account in the select pairing that will occur after establishing the potential social network connection. The Future Connection Engine generates connection recommendations for display to the select pairing based on whether the first and/or the second number of subsequent social network connections satisfies a threshold.

Future connection score of a new connection

Techniques are provided for optimization of user interactions based on connection value scores. A method may comprise receiving input that indicates a selection of one or more social network activities to optimize for a particular member of a social network. The method may also comprise, based on the selection of the one or more social network activities, calculating a connection value score for a social network connection between the particular member and each user in a plurality of other users. Calculating the connection value score may comprise identifying one or more attribute values that are correlated with the one or more social network activities. Further, the method may comprise, based on the connection value score for each user of the plurality of other users, determining a ranking of the plurality of other users. The method may also comprise determining content based on the ranking of the plurality of other users.

Optimization of user interactions based on connection value scores

Growing community of inventors

Mountain View, CA, United States of America

Shilpa Gupta