Microsoft Technology Licensing, LLC

Lea Vega Romero

Adeel Jamil Siddiqui

Prashant Singh Ahluwalia

Xinjian Xue

Balaji Ramasubramaniam

Naveen Duddi Haribabu

Ryan Wang Gao

Bin Pan

Jong-Chin Lin

Onur Tuna

Technologies related to predicting whether a requested change (deployment) in a cloud computing environment will fail are described herein. An exposomic feature value is computed based upon a time series of risk values, where the risk values represent risk of failure over several historic time intervals. A probabilistic model computes a likelihood that the requested deployment will fail during implementation of the requested deployment based upon the exposomic feature value and a contextual feature value, and a notification is transmitted to a computing device of a change manager to allow the change manager to take remedial action.

Computer-implemented exposomic classifier

Growing community of inventors

Redmond, WA, United States of America

Lea Vega Romero