International Business Machines Corporation

VinodKumar Raghavan Nair

Donna Karen Byron

Nadiya Kochura

Timothy B Snow

Donald H Randall, Jr

Derek M Reedy

Monica Sundararajan

Sujana Subedi

Nurdan Vijayadharan

A method for controlling transmission of security audit logs based on a model, a method for controlling transmission of log data based on a model, and a logging system. One embodiment may comprise receiving transmitted log information from a plurality of nodes, applying a rule-based algorithm to the transmitted log information to categorize a first batch of data as included in a security analysis, a second batch of data as excluded from the security analysis, and a third batch of data as actually reviewed in the security analysis based on a user selection, training a classifier based on outcomes of the rule-based algorithm, converting the classifier to run as a trained model executable on the plurality of nodes, and transmitting the trained model executable to the plurality of nodes.

Feedback loop for security audit logs

According to an aspect, software test failures are analyzed using natural language processing (NLP) and machine learning. A failure is detected during a code build associated with a software product. Each change set since a last successful code build associated with the software product is identified and analyzed using NLP to extract change set features. A software defect origin model is applied to the extracted features in each analyzed change set to detect an origin of the failure.

Analyzing software test failures using natural language processing and machine learning

Growing community of inventors

Westford, MA, United States of America

VinodKumar Raghavan Nair