TCP-Net++: Test Case Prioritization Using End-to-End Deep Neural Networks - Deployment Analysis and Enhancements

The increasing number of test cases and frequency of continuous integration in software projects has created a bottleneck in regression testing. To save time and hardware resources, machine learning techniques can be applied without compromising quality. In this work, we present a case study for deployment analysis and results of using our previous work: TCP-Net: Test Case Prioritization using End-to-End Deep Neural Networks [1] in a real-life industrial environment, showing roadblocks, challenges, and enhancements done to improve its performance and usability, achieving 90% to 100% failure coverage by running an average of 23% to 39% of the test cases.