Fraud Analytics with Big Data: A Literature Review on Machine Learning Algorithms in Bankruptcy Prediction and Financial Fraud Detection

This study conducts a systematic literature review on the application of machine learning algorithms in bankruptcy prediction and financial fraud detection. Following the PRISMA protocol, we analyzed relevant articles published between ۱ and Y. from reputable databases. The findings demonstrate that machine learning algorithms, particularly ensemble methods like XGBoost and Random Forest, achieve over ۹.% accuracy, outperforming traditional statistical approaches. Furthermore, integrating numerical data with textual information through natural language processing techniques significantly enhances model performance. Key challenges identified include interpretability issues with complex models, data imbalance problems, and infrastructure requirements. The study concludes that effective implementation of these technologies in auditing requires institutional investments in technical infrastructure and human capital development, alongside research focus on addressing existing limitations. This review provides valuable insights for practitioners and researchers seeking to leverage machine learning in financial analysis and audit processes.

کلیدواژه ها:

Artificial Intelligence ، Machine Learning ، Fraud Detection ، Bankruptcy Prediction ، Systematic Review ، Auditing