IEEE Project Abstract

Assessment of code smell for predicting software change proneness is essential to ensure its significance in thearea of software quality. While multiple studies have been conducted in this regard, the number of systems studied and themethods used in this study are quite different. The objective of this paper is to approve the effect of code smell on the changeinclination of a specific class in a product framework. Further, the paper aims to validate Code Smell for Predicting ClassChange Proneness to find error in prediction of change proneness using code smell. Six typical machine learning algorithms(Naive Bayes Classifier, Multilayer Perceptron, LogitBoost, Bagging, Random Forest, and Decision Tree) have been used topredict change proneness using code smell from a set of 8200 Java classes spanning 14 software systems. Experimental resultssuggest that code smell is indeed a powerful predictor of class change proneness with Multilayer Perceptron being the mosteffective technique. The sensitivity and specificity values for all the models are well over 70% with a few exceptions.