Fault prediction is an important research area that aids software development and the maintenance process. It is a field that has been continuously improving its approaches in order to reduce the fault resolution time and effort. With an aim to contribute towards building new approaches for fault prediction, this paper proposes Entropy Churn Metrics (ECM) based on History Complexity Metrics (HCM) and Churn of Source Code Metrics (CHU). The study also compares performance of ECM with that of HCM. The performance of both these metrics is compared for 14 subsystems of 5different software projects: Android, Eclipse, Apache Http Server, Eclipse C/C++ Development Tooling (CDT), and Mozilla Firefox. The study also analyses the software subsystems on three parameters: (i) distribution of faults, (ii) subsystem size, and (iii) programming language, to determine which characteristics of software systems make HCM or ECM more preferred over others.
In an open source software development environment, it is hard to decide the number of group members required for resolving software issues. Developers generally reply to issues based totally on their domain knowledge and interest, and there are no predetermined groups. The developers openly collaborate on resolving the issues based on many factors, such as their interest, domain expertise, and availability. This study compares eight different algorithms employing machine learning and deep learning, namely—Convolutional Neural Network, Multilayer Perceptron, Classification and Regression Trees, Generalized Linear Model, Bayesian Additive Regression Trees, Gaussian Process, Random Forest and Conditional Inference Tree for predicting group size in five open source software projects developed and managed using an open source development framework GitHub. The social information foraging model has also been extended to predict group size in software issues, and its results compared to those obtained using machine learning and deep learning algorithms. The prediction results suggest that deep learning and machine learning models predict better than the extended social information foraging model, while the best-ranked model is a deep multilayer perceptron((R.M.S.E. sequelize—1.21, opencv—1.17, bitcoin—1.05, aseprite—1.01, electron—1.16). Also it was observed that issue labels helped improve the prediction performance of the machine learning and deep learning models. The prediction results of these models have been used to build an Issue Group Recommendation System as an Internet of Things application that recommends and alerts additional developers to help resolve an open issue.