A case study on machine learning model for code review expert system in software engineering

Abstract

Code review is a key tool for quality assurance in software development. It is intended to find coding mistakes overlooked during development phase and lower risk of bugs in final product. In large and complex projects accurate code review is a challenging task. As code review depends on individual reviewer predisposition there is certain margin of source code changes that is not checked as it should. In this paper we propose machine learning approach for pointing project artifacts that are significantly at risk of failure. Planning and adjusting quality assurance (QA) activities could strongly benefit from accurate estimation of software areas endangered by defects. Extended code review could be directed there. The proposed approach has been evaluated for feasibility on large medical software project. Significant work was done to extract features from heterogeneous production data, leading to good predictive model. Our preliminary research results were considered worthy of implementation in the company where the research has been conducted, thus opening the opportunities for the continuation of the studies.