Risk Prediction by Using Artificial Neural Network in Global Software Development.

Asim Iftikhar,Shahrulniza Musa,Rizwan Ahmed,Muhammad Alam,Mazliham Mohd Su’Ud,Yugen Yi

doi:10.1155/2021/2922728

Abstract

The demand for global software development is growing. The nonavailability of software experts at one place or a country is the reason for the increase in the scope of global software development. Software developers who are located in different parts of the world with diversified skills necessary for a successful completion of a project play a critical role in the field of software development. Using the skills and expertise of software developers around the world, one could get any component developed or any IT-related issue resolved. The best software skills and tools are dispersed across the globe, but to integrate these skills and tools together and make them work for solving real world problems is a challenging task. The discipline of risk management gives the alternative strategies to manage risks that the software experts are facing in today's world of competitiveness. This research is an effort to predict risks related to time, cost, and resources those are faced by distributed teams in global software development environment. To examine the relative effect of these factors, in this research, neural network approaches like Levenberg–Marquardt, Bayesian Regularization, and Scaled Conjugate Gradient have been implemented to predict the responses of risks related to project time, cost, and resources involved in global software development. Comparative analysis of these three algorithms is also performed to determine the highest accuracy algorithms. The findings of this study proved that Bayesian Regularization performed very well in terms of the MSE (validation) criterion as compared with the Levenberg–Marquardt and Scaled Conjugate Gradient approaches.

Highlights

Academic Editor: Yugen Yi e demand for global software development is growing. e nonavailability of software experts at one place or a country is the reason for the increase in the scope of global software development
To examine the relative effect of these factors, in this research, neural network approaches like Levenberg–Marquardt, Bayesian Regularization, and Scaled Conjugate Gradient have been implemented to predict the responses of risks related to project time, cost, and resources involved in global software development
In global software development (GSD), where team members work in different geographical locations and different time zones, the risks related to project time, cost, and resources should be taken into account so that project managers can take better decisions to reduce these risks. is research article is an effort to focus on the implementation of neural network approaches (Levenberg–Marquardt, Bayesian Regularization, and Scaled Conjugate Gradient) to predict overall project risks according to time, cost, and resources which will help decision makers to assess time, budget, and resources needed to conduct a project

Summary

Related Work

In [28], authors established a multilayer feed forward backpropagation-based neural network by utilising seven defect sets of data from the PROMISE repository. For defect prediction in software, three cost sensitive enhanced algorithms have been studied by researchers in [31] to enhance the neural network. It had been observed that threshold moving found as the best option to make the software that is more sensitive in terms of cost It had predicted the defect in software with boosted neural networks among all the algorithms considered exclusively those type of datasets that were developed with the help of object-oriented language. E researchers in [36] used neural network algorithms for predicting physical properties of superconductors and concluded that Levenberg–Marquardt provides the best performance as it gives a fairly accurate prediction for the critical temperature of superconductors which the authors did through plotting SOM (Self Organizing Maps) derived from applying to data set through neuro fuzzy networks. Neural network algorithms may be of great help (i) to narrow down the right materials parameters to work with to prepare new materials in the laboratories and (ii) to accurately predict the critical temperature [37]

Problem Statement

Artificial Neural Network

Research Methodology

Conclusion