AI-Powered Fraud Detection in Auditing Using Machine Learning and Deep Learning Techniques

Financial fraud poses threats to the transparency and integrity of financial systems and therefore requires more advanced detection methods in auditing. This study proposes the application of artificial intelligence, i.e., machine learning (ML) and deep learning (DL) algorithms, to identify fraudulent financial transactions from auditing information. Using a simulated 100 financial transactions dataset with labeled fraud indicators, four classification models were used: Logistic Regression, Random Forest, XGBoost, and Convolutional Neural Network (CNN). Preprocessing was done on the data using normalization and categorical encoding, followed by an 80:20 train-test split. The performance of the models was validated using key metrics such as accuracy, precision, recall, F1-score, and ROC-AUC. Of the models, XGBoost achieved the highest accuracy with 95% and F1-score of 0.93 for the fraud class. The results point to the effectiveness of ensemble and deep learning approaches in detecting fraud with high precision as useful aid to auditors and real-time financial monitoring systems.