Research on Software Defect Detection Based on Random Forest Algorithm

With the increase of software scale and complexity, software defect detection has become a key link in ensuring software quality and system security. Traditional software defect detection methods often rely on static analysis and manual review, resulting in low efficiency and accuracy. This study aims to explore a software defect detection method based on the random forest algorithm. The open NASA MDP dataset is selected, and the random forest algorithm is used to detect and extract feature information from software code. The OOB error method is used to calculate the importance of each feature and sort it in descending order to identify potential defects. The accuracy of this experiment reached 89%, verifying the effectiveness of the random forest model in software defect detection. This study provides an efficient and scalable technical approach for defect detection in future large-scale software systems.