Machine Learning Techniques for Software Bug Prediction: A Systematic Review

Abstract

The goal of software bug prediction is to identify the software modules that will have the likelihood to get bugs by using some fundamental project resources before the real testing starts. Due to high cost in correcting the detected bugs, it is advisable to start predicting bugs at the early stage of development instead of at the testing phase. There are many techniques and approaches that can be used to build the prediction models, such as machine learning. This technique is widely used nowadays because it can give accurate results and analysis. Therefore, we decided to perform a review of past literature on software bug prediction and machine learning so that we can understand better about the process of constructing the prediction model. Not only we want to see the machine learning techniques that past researchers used, we also assess the datasets, metrics and performance measures that are used during the development of the models. In this study, we have narrowed down to 31 main studies and six types of machine learning techniques have been identified. Two public datasets are found to be frequently used and object-oriented metrics are the highly chosen metrics for the prediction model. As for the performance measure, both graphical and numerical measures are often used to evaluate the performance of the models. From the results, we conclude that the machine learning technique can predict the bug, but there are not many applications in this area that exist nowadays. There are a few challenges in constructing the prediction model. Thus, more studies need to be carried out so that a well-formed result is obtained. We also provide a recommendation for future research based on the results we got from this study.

A Study on ML-Based Software Defect Detection for Security Traceability in Smart Healthcare Applications

“…The most widely used data sets in SDP are the Predictor Models in Software Engineering (PROMISE), and NASA Metrics Data Program (MDP)m according to Saharudin et al [ 6 ]. It was observed that 43.3% of each adopted data set was considered in research experiments, while in total usage, 86.6% was due to the open-source nature.…”

“…Performance metrics are important indicators to measure and assess the quality of ML models. Saharudin et al [ 6 ] found that, for SDP, the most widely included types of numerical quantification measurements are Area Under Curve (AUC), based on the results of the Receiver Operating Characteristic (ROC) curve, hqving 56.7%, Recall, with 46.7%, F-Measure/F1-Measure, with 36.7%, Precision, with 30%, Accuracy, with 26.7%, and Other numerical measurements with 76.7%.…”

“…Saharudin et al [ 6 ] found that defects can occur at any stage during the development process, possibly remaining hidden and only becoming active at deployment. This has many real-world consequences or drawbacks, as ever-evolving software becomes more integrated into many aspects of our daily lives.…”

Comprehensive Study on Machine Learning Techniques for Software Bug Prediction

“…Metrics can also be classified based on development phase of software life cycle, into source code level metrics, detailed design level metrics or test level metrics. Objectoriented metrics are often used to assess the testability, maintainability or reusability of source code [20], [35]. Commonly dataset that used for software bug prediction domain is promise repository dataset.…”

Moth Flame Optimization Based FCNN for Prediction of Bugs in Software

“…During the life cycle's development phase, which also includes planning, deployment, design, testing, problem assessment, development, along with continuation, as well as software development life cycle models, machine learning techniques are used to anticipate software bugs. Machine learning techniques and statistical analysis may both be used to anticipate bugs (Saharudin, S.N et al, 2020) [3]. During the software development process, many approaches are employed to get better excellence.…”