Measuring the Fault Predictability of Software using Deep Learning Techniques with Software Metrics

Minimization of failures is the major expectation from reliable software. Predicting the software faults supports in identifying the location in the faulty modules for detailed testing to increase the maintainability. This paper presents fault prediction using some of the deep learning techniques utilizing source code metrics of the software. Accuracy, f-measure, recall, precision, receiver operating characteristic (ROC) curves and area under curve (AUC) values are considered to measure the performance of the deep learning methods. Experimental analysis on five NASA public benchmarked datasets depict Convolutional Neural Network (CNN) classifier as a more robust software fault prediction model achieving the highest accuracy rates. CNN is followed by Artificial Neural Network (ANN) and then Self-Organizing Map (SOM). Learning Vector Quantization (LVQ) version 3 and MultiLVQ have the worst performance on software fault prediction using software metrics.