INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Software Bug Prediction Using Supervised Machine Learning Algorithms
Authors Name:
Sushma
Unique Id:
IJSDR2310062
Published In:
Volume 8 Issue 10, October-2023
Abstract:
The research focuses on predicting software defects to enhance industrial success by providing measurable outcomes for development teams. Identifying defective code areas aids developers in bug pinpointing and optimizing testing efforts. Early detection depends on achieving a high percentage of accurate classification, which is crucial. Although software-defected data sets are large, they are only partially recognized and supported. In contrast to previous research that utilized the Weka simulation tool, In this paper, the machine learning techniques of Logistic Regression, Support Vector Machine (SVM), and Random Forest (RF) are proposed. The systematic analysis measures parameters like confusion, precision, recall, and recognition accuracy, comparing them to existing methods. According to the results, Random Forest had a remarkable accuracy of 98.85% while SVM had an accuracy of 97.75%. However, Logistic Regression lagged behind with 64% accuracy.
Keywords:
Software defects, Logistic Regression, Support Vector Machine (SVM), Random Forest (RF)
Cite Article:
"Software Bug Prediction Using Supervised Machine Learning Algorithms", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 10, page no.358 - 364, October-2023, Available :http://www.ijsdr.org/papers/IJSDR2310062.pdf
Downloads:
000338719
Publication Details:
Published Paper ID: IJSDR2310062
Registration ID:208907
Published In: Volume 8 Issue 10, October-2023
DOI (Digital Object Identifier):
Page No: 358 - 364
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn