Software fault prediction (SFP) is becoming increasingly important in software engineering, especially in service-oriented systems (SOS). This study investigates the effectiveness of using source code for fault prediction in SOS. It uses supervised machine learning algorithms such as random forest, decision tree, and support vector machine to improve error prediction accuracy. Feature extraction is used for more accurate analysis. The study highlights the strengths and weaknesses of these algorithms, providing insights into the prediction of malicious software in SOS. It aims to provide high-performance and reliable software architecture, and advance fault prediction models in SFP.