This paper explores the use of machine learning (ML) and artificial intelligence (AI) to predict supply chain fraud. The study uses real-world business transaction data from a large manufacturing company to train ML and AI models. The findings show that ML and AI classifiers are highly effective in predicting supply chain fraud, with the AI model performing the best across all performance measures. These results suggest that computational intelligence can be a powerful tool for detecting and preventing supply chain fraud. ML and AI can analyze large amounts of data and identify patterns that may be difficult to detect manually. The study also addresses data cleaning, preprocessing, and handling class imbalance issues to improve model performance. The research considers three ML algorithms: logistic regression, random forest, and an AI-based sequential model. The AI sequential model achieved the highest accuracy (99%) in detecting fraudulent transactions. The study also evaluates other performance metrics such as sensitivity, specificity, precision, and F1-score, which indicate that all models performed well in detecting fraudulent transactions. The results show that ML and AI can be effective tools for detecting and preventing supply chain fraud. However, the study also acknowledges the limitations of these technologies, including the need for large amounts of data and the potential for false positives. Future research should focus on improving the accuracy of predictions and exploring the application of these techniques in other domains. The study highlights the potential of ML and AI in enhancing supply chain fraud detection and improving the efficiency of supply chain management.This paper explores the use of machine learning (ML) and artificial intelligence (AI) to predict supply chain fraud. The study uses real-world business transaction data from a large manufacturing company to train ML and AI models. The findings show that ML and AI classifiers are highly effective in predicting supply chain fraud, with the AI model performing the best across all performance measures. These results suggest that computational intelligence can be a powerful tool for detecting and preventing supply chain fraud. ML and AI can analyze large amounts of data and identify patterns that may be difficult to detect manually. The study also addresses data cleaning, preprocessing, and handling class imbalance issues to improve model performance. The research considers three ML algorithms: logistic regression, random forest, and an AI-based sequential model. The AI sequential model achieved the highest accuracy (99%) in detecting fraudulent transactions. The study also evaluates other performance metrics such as sensitivity, specificity, precision, and F1-score, which indicate that all models performed well in detecting fraudulent transactions. The results show that ML and AI can be effective tools for detecting and preventing supply chain fraud. However, the study also acknowledges the limitations of these technologies, including the need for large amounts of data and the potential for false positives. Future research should focus on improving the accuracy of predictions and exploring the application of these techniques in other domains. The study highlights the potential of ML and AI in enhancing supply chain fraud detection and improving the efficiency of supply chain management.