A Systematic Review of Unsupervised Learning Techniques for Software Defect Prediction
This review addresses software practitioners by evaluating unsupervised methods to reduce reliance on labeled data, but it is incremental as it synthesizes existing studies rather than introducing new techniques.
The paper conducted a systematic review of unsupervised learning techniques for software defect prediction, analyzing 49 studies with 2456 results and finding that unsupervised models perform comparably to supervised models, with Fuzzy CMeans and Fuzzy SOMs being the best performers, but also identified issues like 11% inconsistent results and 33% incomplete reporting.
Background: Unsupervised machine learners have been increasingly applied to software defect prediction. It is an approach that may be valuable for software practitioners because it reduces the need for labeled training data. Objective: Investigate the use and performance of unsupervised learning techniques in software defect prediction. Method: We conducted a systematic literature review that identified 49 studies containing 2456 individual experimental results, which satisfied our inclusion criteria published between January 2000 and March 2018. In order to compare prediction performance across these studies in a consistent way, we (re-)computed the confusion matrices and employed the Matthews Correlation Coefficient (MCC) as our main performance measure. Results: Our meta-analysis shows that unsupervised models are comparable with supervised models for both within-project and cross-project prediction. Among the 14 families of unsupervised model, Fuzzy CMeans (FCM) and Fuzzy SOMs (FSOMs) perform best. In addition, where we were able to check, we found that almost 11% (262/2456) of published results (contained in 16 papers) were internally inconsistent and a further 33% (823/2456) provided insufficient details for us to check. Conclusion: Although many factors impact the performance of a classifier, e.g., dataset characteristics, broadly speaking, unsupervised classifiers do not seem to perform worse than the supervised classifiers in our review. However, we note a worrying prevalence of (i) demonstrably erroneous experimental results, (ii) undemanding benchmarks and (iii) incomplete reporting. We therefore encourage researchers to be comprehensive in their reporting.