FULL PDF
Abstract
Software reliability prediction plays a crucial role in the software development lifecycle by allowing developers to anticipate system failures based on historical defect data. This paper proposes a software reliability prediction model that leverages historical defect metrics and machine learning techniques to predict potential software failures. By using defect data such as the number of reported defects and their severity, coupled with machine learning algorithms such as Random Forest and Support Vector Machines (SVM), we aim to improve the accuracy and efficiency of predicting software reliability. Our results demonstrate a promising approach to software reliability prediction, with a comparative analysis of various machine learning techniques and their respective performance in terms of precision, recall, and F1-score.
View more >>