Treffer: The Ability of Search-Based Algorithms to Predict Change-Prone Classes.

Evolving requirements, technological advancements, and defects are crucial sources of software change during the maintenance phase. In such a scenario, detection and prediction of change-prone classes is essential for effective and efficient use of limited resources. Knowledge of change-prone classes in the early phases of the software development life cycle leads to better quality software, as these classes are rigorously tested and tracked. Search-based algorithms (SBAs) are search procedures that can find a near optimal solution for a problem with the help of a fitness function. The aim of this article is to analyze the effectiveness of SBAs on the change proneness prediction problem. Few studies in the literature have assessed the applicability of statistical and machine learning (ML) methods for identifying change-prone classes. In this work, the authors compare and assess the performance of SBAs with both ML and logistic classifiers. To validate the results, they used three open-source data sets developed in the Java language. The study shows that the performance of SBAs is comparable to, and even better in some cases, than ML and statistical methods. Thus, SBAs can be used for efficient resource utilization during the maintenance and testing phases of the software development life cycle. [ABSTRACT FROM AUTHOR]

Copyright of Software Quality Professional is the property of American Society for Quality, Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)