Classification of Software Defect Prediction for Bisnissyariah.co.id Media Portal using Machine Learning Technology

Abstract

This research was conducted to develop software defect prediction using a dataset from Bisnissyariah, a forum website with up-to-date news related to Islamic business. The study employed a straightforward research design to ensure easy comprehension for the readers. Machine learning models, including Random Forest, Gradient Boosting, and Support Vector Machine, were utilized in this research—the application of these models aimed to evaluate and compare the accuracy of software defect predictions. The research findings indicated that the Random Forest model outperformed the others, achieving an accuracy rate of 96.7%. This result shows the high effectiveness of the Random Forest model in predicting software defects based on data from Bisnissyariah. In addition, these findings significantly impact the development of more reliable and high-quality software, particularly in Islamic business. This research makes a valuable contribution to enhancing our understanding of software defect prediction using data from sources like Bisnissyariah.