Machine learning based Software Fault Prediction models

Abstract

The study aims to identify soft-computing-based software fault prediction models that assist in resolving issues related to the quality, reliability, and cost of the software projects. It proposes models for implementation of software fault prediction using decision-tree regression and the K-nearest neighbor technique of machine learning. The proposed models have been designed and implemented in Python using designed metric suites as input, and the predicted-faults as output, for the real-time, wider dataset from the Promise repository. By comparing the prediction and validation results of the proposed models for the same dataset, it has been concluded that the decision-tree regression-based fault prediction model has the best performance with values of MMRE, RMSE, and accuracy of 0.0000204, 3.54, and 99.37, respectively.