Software Quality Prediction Using Machine Learning

In today's fast-changing environment, in order to create much more stable and complex software programs. With the emergence of Machine Learning, many companies are increasingly embracing this revolutionary approach, both in terms of growth and maintenance, to reduce software costs. As the size of applications increases in terms of functionality, when designing test cases, Software Quality Prediction is becoming more complex. Since the software measurement mechanism in a constant cycle has several benefits, namely reliable project cost estimation, process improvement and product quality compliance, it is vital to try further analysis of software metrics in order to implement the use of machine learning in software quality prediction. This research aimed at building two models which is Software Defect Prediction Model (SDPM) which will be used to predict defects in software and Software Maintainability Prediction Model (SMPM) which will be used for Software Maintainability. Different classifiers, namely Random Forest, Decision Tree, Naive Bayes and Artificial Neural Networks have been considered and then evaluated using different metrics such as Accuracy, Precision, Recall and Area Under the Curve (AUC). The two models have successfully been evaluated and Decision Tree has been chosen as compared to other classifiers which tends to perform much better for both models. These models have been eventually been deployed as web services. Finally a framework based on a set of guidelines that can be used to improve software quality has been devised.