The Comparing Logistic Regression and Random Forest Performance in Predicting Financial Distress among Technology Companies Listed on the Indonesia Stock Exchange

Abstract

The growth of Indonesia’s technology sector, accompanied by intensifying business competition and economic uncertainty, exposes companies to financial distress risk. Early detection is important to help companies, investors, and stakeholders make appropriate decisions. This study aims to analyze and compare Logistic Regression and Random Forest performance in predicting financial distress among technology companies listed on the Indonesia Stock Exchange (IDX) during 2021–2025. A quantitative approach was employed using secondary data from the annual financial statements of 41 technology companies selected through purposive sampling, yielding 205 observations. The predictors comprise Return on Assets (ROA), Net Profit Margin (NPM), Debt to Equity Ratio (DER), Current Ratio (CR), Interest Coverage Ratio (ICR), Total Asset Turnover (TATO), and Total Debt (TH). Orange Data Mining was used for analysis, with 80% of the data allocated to training and 20% to testing. Model performance was evaluated using accuracy, precision, recall, and F1-score. Random Forest outperformed Logistic Regression, achieving accuracy of 92.7%, precision of 94.5%, recall of 92.7%, and an F1-score of 93.0%. Logistic Regression achieved accuracy of 82.9%, precision of 83.7%, recall of 82.9%, and an F1-score of 83.2%. Feature importance analysis identified Net Profit Margin (NPM) as the most influential predictor of financial distress. Random Forest is therefore considered more effective than Logistic Regression in identifying potential financial distress among technology companies.