Risk Classification in Global Software Development Using a Machine Learning Approach: A Result Comparison of Support Vector Machine and K-Nearest Neighbor Algorithms

Risk Classification in Global Software Development Using a Machine Learning Approach: A Result Comparison of Support Vector Machine and K-Nearest Neighbor Algorithms

Asim Iftikhar, Shahrulniza Musa, Muhammad Mansoor Alam, Rizwan Ahmed, Mazliham Mohd Su'ud, Laiq Muhammad Khan, Syed Mubashir Ali
Copyright: © 2022 |Pages: 21
DOI: 10.4018/JITR.299385
Article PDF Download
Open access articles are freely available for download

Abstract

Software development through teams at different geographical locations is a trend of modern era, which is not only producing good results without costing lot of money but also productive in relation to its cost, low risk and high return. This shift of perception of working in a group rather than alone is getting stronger day by day and has become an important planning tool and part of their business strategy. In this research classification approaches like SVM and K-NN have been implemented to classify the true positive events of global software development project risk according to Time, Cost and Resource. Comparative analysis has also been performed between these two algorithms to determine the highest accuracy algorithms. Results proved that Support Vector Machine (SVM) performed very well in case of Cost Related Risk and Resource Related Risk. Whereas, KNN is found superior to SVM for Time Related Risk.
Article Preview
Top

Introduction

Software development environment is shifting from centralized to a dispersed environment so as to offer advantages over the conventional techniques in the recent years (Al-Zaidi & Qureshi, 2017). Success progressively relies upon utilizing software as a competitive weapon. Over 10 years back, looking for lower costs and access to skilled resources, numerous software firms started to explore or experiment with dispersed software development facilities and with outsourcing (Prikladnicki et al., 2003). Therefore, software development is progressively a multisite, multicultural, globally dispersed endeavor. Designers, Engineers, managers, and officials face various, imposing challenges on many levels, from the specialized to the social and cultural (Herbsleb & Moitra, 2001; Prikladnicki et al., 2003). Different scholars name such teams remotely dispersed at various locations or Global Software Development environment (GSD) environment (Iftikhar et al., 2018b).

Global Software Development

The term GSD implies the teams of software experts are scattered, they are located in different geographical locations for the purpose of developing a software on same set of goals and objectives. These teams belong to different cultures and different development backgrounds (Colomo-Palacios et al., 2012). It uses digital communication networks facility to communicate with each other. GSD is popular among the IT organization and a large number of IT employees are taking up global assignment, due to its benefits it offers, irrespective of the duration (Arumugam & Kaliamourthy, 2016). There are some of the significant benefits of GSD that includes continuous development that enhances product quality. It also minimizes costs using cheaper labor and material resources that contributes to increasing productivity. (Al-Zaidi & Qureshi, 2017; AL_Zaidi & Qureshi, 2014; Anjum et al., 2006). In GSD environment distributed teams are still facing many challenges during global software development process such as strategic issues, cultural issues, Inadequate communication, distance, different backgrounds and project and process management issues (Casey & Richardson, 2009; Herbsleb & Moitra, 2001) as shown in Figure 1 (Carmel, 1999).

Figure 1.

GSD Challenges (Carmel, 1999)

JITR.299385.f01

GSD projects are generally extensive and global evolution steers them to become complicated which in term makes them less probable to succeed. Distributed projects are more likely not to succeed reason being ‘‘physical existence of individuals, time zones, cultural issues, organizational, and stakeholder distances negatively inñuence communication and knowledge exchange between onshore and offshore project team members’’ (Fabriek et al., 2008). When a project is to be executed beyond borders, the assessments of a project manager maximize as the manager now has to take into consideration the difference in time zones, lingual problems, the overall context and also the built of the specific project (AL_Zaidi & Qureshi, 2014; Hossain et al., n.d.). Global Software development environment made project management task more hectic due to its challenges and complex processes (Colomo-Palacios et al., 2014). Developing software projects to address business needs and requirements in global software development environment is so exceedingly complex and troublesome that it is common for software projects to overrun budgets and exceed scheduled completion dates.

Complete Article List

Search this Journal:
Reset
Volume 16: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 15: 6 Issues (2022): 1 Released, 5 Forthcoming
Volume 14: 4 Issues (2021)
Volume 13: 4 Issues (2020)
Volume 12: 4 Issues (2019)
Volume 11: 4 Issues (2018)
Volume 10: 4 Issues (2017)
Volume 9: 4 Issues (2016)
Volume 8: 4 Issues (2015)
Volume 7: 4 Issues (2014)
Volume 6: 4 Issues (2013)
Volume 5: 4 Issues (2012)
Volume 4: 4 Issues (2011)
Volume 3: 4 Issues (2010)
Volume 2: 4 Issues (2009)
Volume 1: 4 Issues (2008)
View Complete Journal Contents Listing