Financial crises in companies can cause significant economic losses and affect investors, stakeholders, and the overall market stability. Therefore, identifying early warning signals of financial distress has become an important research problem in financial analytics. This study proposes a machine learning–based financial crisis early warning system for listed companies using historical financial and economic indicators. The dataset used in this research contains multiple financial attributes such as revenue, net profit, total assets, total liabilities, operating ratio, current ratio, debt-to-equity ratio, return on assets (ROA), return on equity (ROE), and stock return. In addition to company financial metrics, macroeconomic indicators including interest rate, inflation rate, and GDP growth are also considered to improve prediction performance. Data preprocessing techniques such as cleaning, normalization, and feature selection are applied to enhance the quality of the dataset before model training. Machine learning algorithms are then utilized to analyze patterns in financial indicators and classify companies into crisis and non-crisis categories. The proposed system helps detect potential financial instability at an early stage and provides valuable insights for financial analysts, investors, and policymakers. Experimental results demonstrate that machine learning techniques can effectively identify financial risk patterns and improve the accuracy of financial crisis prediction.
Mahesh et al. (Sun,) studied this question.