Research on Automatic Financial Statement Audit Algorithm Integrating Deep Learning and Machine Learning
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
With the rapid growth of AI and increasingly complex financial data, traditional manual auditing is inefficient and error-prone. This paper proposes an automatic financial statement audit algorithm integrating deep learning (LSTM, Autoencoder) and machine learning (Random Forest, XGBoost). Experiments on over 10,000 real-world financial reports show the hybrid method achieves 94% accuracy, 93% precision, 92% recall, and 92.5% F1-score, outperforming standalone ML or DL approaches by 6–9%. The results demonstrate that combining deep learning with machine learning significantly improves audit accuracy and efficiency.
Fields of Study & Subjects
Robotic Process Automation Applications
Auditing
Earnings Management
Governance
Stock Market Forecasting Methods
Publication details
- Journal / source
- IEEE International Conference on Power, Electronics and Green Energy (ICPEGE)
- Pages
- 1293–1297
- Publication date
- 28 January 2026
- Language
- EN