Going concern audit: modern methods of analysis and evaluation

This article explores modern methods used in assessing going concern within financial audits, highlighting the shift from traditional, indicator-based evaluations to advanced techniques powered by artificial intelligence and machine learning. Models such as neural networks, LSTM, GRU, and NLP tools enable auditors to detect financial risks early, analyze patterns in large datasets, and predict insolvency with high accuracy. Additionally, stress testing and hybrid models improve forecasting capabilities. While automation enhances audit quality, concerns remain about transparency, data bias, and the need for specialized training. The study emphasizes a balanced approach that combines technological tools with auditor judgment.