Predicting Change Prone Classes in Open Source Software

Abstract

In today's world, the heart of modern technology is software. In order to compete with pace of new technology, changes in software are inevitable. This article aims at the association between changes and object-oriented metrics using different versions of open source software. Change prediction models can detect the probability of change in a class earlier in the software life cycle which would result in better effort allocation, more rigorous testing and easier maintenance of any software. Earlier, researchers have used various techniques such as statistical methods for the prediction of change-prone classes. In this article, some new metrics such as execution time, frequency, run time information, popularity and class dependency are proposed which can help in prediction of change prone classes. For evaluating the performance of the prediction model, the authors used Sensitivity, Specificity, and ROC Curve. Higher values of AUC indicate the prediction model gives significant accurate results. The proposed metrics contribute to the accurate prediction of change-prone classes.

Machine Learning for Change-Prone Class Prediction: A History-Based Approach

“…The authors highlight that machine learning is a promising approach and is a tendency, adopted in more recent works. Godara et al (2018) and Kumar et al (2019) investigate the use of metrics to predict change-prone classes. While the work of Godara et al (2018) relied on the bee colony algorithm (Karaboga, 2005) to perform its predictions, Kumar et al (2019) addresses the use of machine learning.…”

“…Godara et al (2018) and Kumar et al (2019) investigate the use of metrics to predict change-prone classes. While the work of Godara et al (2018) relied on the bee colony algorithm (Karaboga, 2005) to perform its predictions, Kumar et al (2019) addresses the use of machine learning. The work of Kumar et al (2019) used 18 machine learning algorithms, including Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), among others.…”

Enhancing Behavioral Dependency for Effective Computing in Software

“…One of the major reasons of software failure is incapability to understand the changing requirements and uncontrolled change propagation. Godara et al (2018) suggested that classes which are prone to changes needs major consideration as these involve more effort and higher amount of maintenance costs and development costs.…”