Supreeth Chandrashekhar

Development Engineer at Philips HealthCare

“I’m a Software Engineer, passionate about building and certifying the quality of Software product in Business Analytics/ Web / API / Hadoop & Big Data Technologies. I have worked on cutting-edge products at Cisco Systems, Vizury Interactive solutions, and Philips Healthcare.

I play a current role of development engineer focused on engineering a data repository for Analytics platform.”

Understanding the Usage, Impact, and Adoption of Deep Learning in Software Quality

The test quality (Coverage, Scenarios, and Defects) is one of the most important pieces of any software system. However, due to the unknown limitations of product understanding or missed scenarios to test would result in an impact on the overall quality of the software system.
There are various studies which suggest’ s on improving test quality, however, most of the studies miss the key ingredients of application logs and software repositories, for example, GitHub and Bug tracking systems.

To uncover the reasons behind the lack of software quality in systems, we conducted a mix-method study, mining logs from various applications of a similar domain, gathering test scenario and mapping it to the workflow and getting insights on a developer by analyzing the code, number of check-ins and defects introduced or captured against the workflows by leveraging the power of deep learning.

This perspective is particularly important since the management doesn’t have to just rely on only the test cases which are tested by the development and test teams. This platform would be able to help to improvise the overall quality of test coverage, appropriate developer to work on a given module or fix a defect along with its pre and post impacts.