Prediction and Comparison of Bankruptcy Models in Banking Sector Companies in Indonesia

Abstract

The Covid-19 pandemic, coupled with the economic recession from 2019 to 2022, has adversely impacted various industries, leading to bankruptcies. Among the affected sectors, the banking industry faced significant challenges, experiencing disruptions in credit processes and fund distribution due to diminished purchasing power. This situation poses a severe threat to the banking sector, necessitating the monitoring of financial conditions through bankruptcy analysis as an early warning system for company performance. This study investigates potential differences in the results of financial distress prediction models—Altman, Springate, Zmijewski, Grover, and Ohlson—during the abnormal conditions of the Covid-19 pandemic. Using purposive sampling of banking companies listed on the IDX from 2019 to 2022, the study divided the samples into financial distress and non-financial distress categories. Analysis involved tests for multicollinearity assumptions, logistic regression, and accuracy/error rate calculations. The findings reveal variations in the predictive abilities of the Altman, Springate, Zmijewski, Grover, and Ohlson models. The Grover model emerged as the most accurate, with a 60% accuracy rate in predicting bankruptcy, while Altman, Springate, and Zmijewski models demonstrated low predictive values (0%, 0%, and 15% accuracy, respectively). The simplicity of the Grover model's measurement indicators, incorporating capital adequacy, EBIT, and ROA, offers a comprehensive view of bankruptcy prediction ratios. Moreover, stringent internal risk analysis and external factors, such as regulatory interventions, contribute to keeping banks resilient amid global economic crises. The research suggests that banking companies can benefit from employing the Grover method for bankruptcy analysis as part of their future anticipation strategy.