NRPredictor: an ensemble learning and feature selection based approach for predicting the non-reproducible bugs

Kulbhushan Bansal (), Gopal Singh (), Sunesh Malik () and Harish Rohil ()
Additional contact information
Kulbhushan Bansal: Chaudhary Devi Lal University
Gopal Singh: Maharshi Dayanand University
Sunesh Malik: Maharaja Surajmal Institute of Technology
Harish Rohil: Chaudhary Devi Lal University

International Journal of System Assurance Engineering and Management, 2023, vol. 14, issue 3, No 14, 989-1009

Abstract: Abstract Software maintenance is essential and significant phase of software development life cycle. In software projects, issue tracking systems are used to collect, categorise, and track filed issues. The distinct bug reports are not being able to reproduced by software developers and hence, marked as non-reproducible. Non-reproducible problems are a major performance issue in bug repositories since they take up a lot of time and effort from developers. The goal of this paper is to create a prediction model for detecting non-reproducible bugs. Due to sheer unexpected nature of bug fixation, bug management is frequently a painful undertaking for software engineers. Non reproducible bugs add to the difficulty of this vexing indexing. This paper deals with the development of a early prediction model for identification of non-reproducible bugs. In this work, a novel framework named NRPredictor, has been proposed which uses three ensemble learning and one feature selection algorithm for Non-Reproducible bug prediction. The prediction performance of the proposed framework has been examined using projects of Bugzilla bug tracking system. Three open-source projects viz. Mozilla Firefox, Eclipse and NetBeans have been used for evaluating the prediction performance. While forecasting the fixability of bug reports, the experimental findings reveal that NRPredictor surpasses traditional machine learning techniques. For Mozilla Firefox, Eclipse, and NetBeans projects, NRPredictor, delivers performance (in terms of F1-score) up to 88.3, 87.8, and 87.4% respectively. An improvement in performance up to 6.1, 5 and 2.7% has been obtained for NetBeans, Eclipse, and Mozilla Firefox projects, respectively as compared to the best performing standalone machine learning classifier.

Keywords: Non-reproducible bugs; Reproducible bugs; Machine learning; Classification; Ensemble learning; Feature selection; Fixability prediction; Mining software repositories (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s13198-023-01902-7 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:ijsaem:v:14:y:2023:i:3:d:10.1007_s13198-023-01902-7

Ordering information: This journal article can be ordered from
http://www.springer.com/engineering/journal/13198

DOI: 10.1007/s13198-023-01902-7

Access Statistics for this article

International Journal of System Assurance Engineering and Management is currently edited by P.K. Kapur, A.K. Verma and U. Kumar

More articles in International Journal of System Assurance Engineering and Management from Springer, The Society for Reliability, Engineering Quality and Operations Management (SREQOM),India, and Division of Operation and Maintenance, Lulea University of Technology, Sweden
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().