Microsoft Technology Licensing, LLC

Balaji Ramasubramaniam

Adeel Jamil Siddiqui

Xinjian Xue

Ryan Wang Gao

Naveen Duddi Haribabu

Jong-Chin Lin

Bin Pan

Prashant Singh Ahluwalia

Onur Tuna

Lea Vega Romero

Technologies relating to model interpretation are described herein. A text classifier is provided with input text and assigns a class to the input text from amongst several possible classes. Based upon the class assigned to the input text by the text classifier, a class profile of a centroidal classifier is selected, where the class profile is constructed based upon numerous input texts to which the text classifier has previously assigned the class. Based upon the selection of the class profile, information that is indicative of operation of the text classifier with respect to the text classifier assigning the class to the input text is output, where the information includes an exemplar text sequence.

Interpreting text classifier results with affiliation and exemplification

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

Balaji Ramasubramaniam