Experimental Study on Software Fault Prediction Using Machine Learning Model

Abstract

Faults are the leading cause of time consuming and cost wasting during software life cycle. Predicting faults in early stage improves the quality and reliability of the system and also reduces cost for software development. Many researches proved that software metrics are effective elements for software fault prediction. In addition, many machine learning techniques have been developed for software fault prediction. It is important to determine which set of metrics are effective for predicting fault by using machine learning techniques. In this paper, we conduct an experimental study to evaluate the performance of seven popular techniques including Logistic Regression, K-nearest Neighbors, Decision Tree, Random Forest, Naive Bayes, Support Vector Machine and Multilayer Perceptron using software metrics from Promise repository dataset usage. Our experiment is performed on both method-level and class-level datasets. The experimental results show that Support Vector Machine archives a higher performance in class-level datasets and Multilayer Perception produces a better accuracy in method-level datasets among seven techniques above.