An Audit of Machine Learning Experiments on Software Defect Prediction

TL;DR

This paper audits recent machine learning studies on software defect prediction, revealing wide variability in experimental practices, limited reproducibility, and highlighting the need for improved reporting standards.

Contribution

It provides a comprehensive analysis of experimental design and reproducibility issues in recent SDP studies, offering insights for better research practices.

Findings

Approximately 1,585 experiments identified in recent literature.

Only about 45% of studies used formal statistical inference.

Reproducibility varied from near complete to severely limited.

Abstract

Background: Machine learning algorithms are widely used to predict defect prone software components. In this literature, computational experiments are the main means of evaluation, and the credibility of results depends on experimental design and reporting. Objective: This paper audits recent software defect prediction (SDP) studies by assessing their experimental design, analysis, and reporting practices against accepted norms from statistics, machine learning, and empirical software engineering. The aim is to characterise current practice and assess the reproducibility of published results. Method: We audited SDP studies indexed in SCOPUS between 2019 and 2023, focusing on design and analysis choices such as outcome measures, out of sample validation strategies, and the use of statistical inference. Nine study issues were evaluated. Reproducibility was assessed using the instrument proposed by Gonz\'alez Barahona and Robles. Results: The search identified approximately 1,585 SDP experiments published during the period. From these, we randomly sampled 101 papers, including 61 journal and 40 conference publications, with almost 50 percent behind paywalls. We observed substantial variation in research practice. The number of datasets ranged from 1 to 365, learners or learner variants from 1 to 34, and performance measures from 1 to 9. About 45 percent of studies applied formal statistical inference. Across the sample, we identified 427 issues, with a median of four per paper, and only one paper without issues. Reproducibility ranged from near complete to severely limited. We also identified two cases of tortured phrases and possible paper mill activity. Conclusions: Experimental design and reporting practices vary widely, and almost half of the studies provide insufficient detail to support reproduction. The audit indicates substantial scope for improvement.