About this document

Software Defect Prediction Using ML Techniques by NL Joha is a document available to read on EtoBox.

The article discusses a study on software defect identification using machine learning (ML) and explainable artificial intelligence (XAI) techniques. It evaluates thirteen ML models on four datasets, concluding that the XGBR model performed best in terms of accuracy and error metrics. The study also highlights the significance of features such as the number of static invocations and coupling between objects in predicting software faults, with LIME providing the most accurate feature explanations.

Author

NL Joha

Language

EN