Bankruptcy Prediction in Indonesian Retail Firms: Altman and Springate Models

Abstract

Indonesia's retail subsector has faced considerable financial challenges due to fluctuations in purchasing power, widespread store closures, and intense competition from the e-commerce ecosystem. This study examines and compares the accuracy of the Modified Altman Z-Score (Z"-Score) and Springate (S-Score) models in predicting bankruptcy among retail subsector companies listed on the Indonesia Stock Exchange (IDX) during 2019–2024. A comparative quantitative approach with purposive sampling was employed. The sample comprised eight daily consumer-goods and apparel/department-store retailers, yielding 48 firm-year observations; specialized electronics retailers were excluded to avoid inventory-cycle bias. Classification performance was evaluated using a confusion matrix—accuracy, sensitivity, specificity, precision, and F1-score—and the McNemar test was used to assess whether the models differed significantly. The Springate model achieved 97.92% accuracy (47 of 48 observations correctly classified), with 100.00% sensitivity, 96.77% specificity, 94.44% precision, and a 97.14% F1-score. The Altman Z-Score model achieved 91.67% accuracy (44 of 48 observations correctly classified), with 94.12% sensitivity, 90.32% specificity, 84.21% precision, and an 88.89% F1-score. Although Springate produced higher numerical accuracy, the McNemar test yielded a p-value of 0.655 (> 0.05), indicating no statistically significant difference between the two models. Both models are effective early-warning instruments for stakeholders.