Quantum vs. Classical Machine Learning Algorithms for Software Defect Prediction: Challenges and Opportunities

TL;DR

The paper addresses software defect prediction by benchmarking three quantum ML (PQSVC, QSVC, VQC) and five classical ML (SVC, RF, KNN, GBC, PCT) algorithms across 20 datasets. It employs dimensionality reduction (Pearson correlation to 32 features, then SelectKBest to 15) and a fixed 70/30 train/test split to ensure fair comparisons, reporting accuracy, precision, recall, F1, and runtime. The study finds that QSVC often delivers higher recall and F1 (best in 13/20 datasets) but classical models excel in precision, highlighting trade-offs and the current practical limits of QML. It also discusses challenges such as limited real quantum hardware, qubit constraints, and interpretability, and suggests future work on hybrid ensembles and hardware validation to advance defect prediction with quantum methods.

Abstract

Software defect prediction is a critical aspect of software quality assurance, as it enables early identification and mitigation of defects, thereby reducing the cost and impact of software failures. Over the past few years, quantum computing has risen as an exciting technology capable of transforming multiple domains; Quantum Machine Learning (QML) is one of them. QML algorithms harness the power of quantum computing to solve complex problems with better efficiency and effectiveness than their classical counterparts. However, research into its application in software engineering to predict software defects still needs to be explored. In this study, we worked to fill the research gap by comparing the performance of three QML and five classical machine learning (CML) algorithms on the 20 software defect datasets. Our investigation reports the comparative scenarios of QML vs. CML algorithms and identifies the better-performing and consistent algorithms to predict software defects. We also highlight the challenges and future directions of employing QML algorithms in real software defect datasets based on the experience we faced while performing this investigation. The findings of this study can help practitioners and researchers further progress in this research domain by making software systems reliable and bug-free.

Figures (3)

• Figure 1: Overall Methodology
• Figure 2: Comparing Run Time on Different Dataset Size using QSVC Algorithm
• Figure 3: Average Precision, Recall, and F1 Scores for CML and QML algorithms are illustrated in this figure. CML algorithms are depicted in dark colors, while QML algorithms are represented in lighter shades