Machine learning in software defect prediction: A Business-Driven Systematic Literature Review

noindent textbf{Context:} Machine learning software defect prediction is a promising field of software engineering, attracting much attention from the research community; however, its industry application lags behind academic achievements. noindent textbf{Objective:} This study aims to evaluate the business applicability of machine learning software defect prediction and gather lessons learned. It is a part of a larger project focused on improving the quality and minimising the cost of software testing of the 5G system at Nokia. noindent textbf{Method:} The systematic literature review was performed among conference and journal articles published between 2015 and 2022 in the most popular online databases. A quasi-gold standard procedure was used to validate the search, and PRISMA 2020 guidelines were used for transparency, reporting purposes and replicability. noindent textbf{Results:} We have selected and analysed 45 publications out of 397 found by our automatic search (and seven by snowballing). We have identified high-quality evidence of used methods, metrics, frameworks, and datasets. However, we found a minimal emphasis on practical lessons learned and cost-consciousness --- both vital from a business perspective. noindent textbf{Conclusions:} Despite the number of machine learning software defect prediction studies validated in the industry is increasing and we were able to identify several excellent papers is done in vivo, there is still not enough focus on the business aspects of the effort that would help bridge the gap between the needs of the industry and academic research.