A COMPARATIVE STUDY OF ANN AND LOGISTIC REGRESSION FOR FINANCIAL DISTRESS PREDICTION IN INDONESIAN MANUFACTURING FIRMS

This study aims to compare the predictive performance of the Logistic Regression (LR) model and the Artificial Neural Network (ANN) in forecasting financial distress among manufacturing firms listed on the Indonesia Stock Exchange (IDX) during 2022–2024. Financial distress represents a deterioration in a company’s financial condition and serves as an early warning of potential bankruptcy; therefore, accurate prediction models are crucial for investors, creditors, and corporate decision-makers. The sample comprises manufacturing companies selected through purposive sampling, based on the availability and completeness of financial statements for the observation period. The variables used include financial ratios such as Return on Assets (ROA), Debt-to-Assets Ratio (DAR), and Current Ratio (CR). Two predictive models were developed: Logistic Regression, a conventional statistical approach, and an Artificial Neural Network, a nonlinear machine learning method. The results indicate that the Logistic Regression model achieves a higher recall rate than the Artificial Neural Network model (55.56%), suggesting that Logistic Regression provides better predictive performance in identifying companies experiencing financial distress.