Intelligent detection of fraud in financial statements using deep learning and XGBoost

Fraud is a phenomenon that involves deviations and manipulations in financial statements.These actions can lead to tax non-compliance and erode the trust stakeholders.Given and vast amount of financial data within organizations, leveraging artificial intelligence as a sophisticated tool can greatly enhance fraud detection in financial statements and bolster confidence in the face of evolving fraudulent tactics.This paper introduces an intelligent method for detecting fraud in financial statements.Initially, the Apriori algorithm is utilized to select pertinent features in the financial data.Subsequently, the performance of the proposed method is enhanced by augmenting the dataset using the GAN-CNN network.Finally, fraud detection is executed with the assistance of XGBoost.The proposed model is evaluated on a comprehensive financial dataset from Kaggle.The results demonstrate that the proposed method achieves superior performance with an accuracy of 96.21%, a precision of 96.02%, a recall of 95.41%, and an F1-score of 93.99%, significantly outperforming benchmark models such as 1D-CNN, LSTM, and Bi-LSTM.Furthermore, a sensitivity analysis reveals that the model maintains robust performance (accuracy >94%) across varying training data sizes and is not overly sensitive to the key hyperparameters of the GAN and XGBoost components, confirming its stability and generalizability.