Evaluating Precision: Comparing Altman, Springate, Zmijewski, and Grover Models in Financial Distress Prediction

This research examines the accuracy of Altman, Springate, Zmijewski, and Grover methods in predicting financial distress at PT Garuda Indonesia Tbk during 2017–2021. The population comprises all financial reports of the company, with a saturated sampling technique applied. Data collection utilized documentation methods, and analysis involved descriptive tests and accuracy level evaluations. Results indicate that the Zmijewski method is the most accurate, with an 80% accuracy rate, followed by the Altman method at 60%, and both Springate and Grover methods at 40%. The Zmijewski method shows the highest Type I error rate at 20%, while Altman, Springate, and Grover methods have 0% Type I error rates. Regarding Type II errors, Zmijewski exhibits the highest rate at 80%, Grover at 60%, Altman at 40%, and Springate at 20%. The findings suggest that financial distress prediction methods are valuable tools for management to monitor the company's financial health and ensure operational sustainability. Adopting accurate prediction models can support decision-making and mitigate risks associated with financial distress