Literature Analysis on Financial Distress and Bankruptcy Prediction

Abstract

Objective: This study aims to analyze financial distress prediction models that have been used in various academic studies, evaluate the accuracy of models in various industry sectors, and identify factors that affect the accuracy of predicting corporate bankruptcy.
Research Design & Methods: This research uses a systematic literature review (SLR) to evaluate the effectiveness of financial distress prediction models based on studies from reputable journals in the range 2015-2024.
Findings: The results show that the Altman Z-Score and Ohlson O-Score have the highest accuracy rate (90.91%), making them the most widely used models in the manufacturing and banking industries. The Zmijewski Model has an accuracy of 86.36%, more suitable for high asset-based sectors such as mining and transportation. The Springate Model, with an accuracy rate of 63.64% - 73.48%, is simpler but less accurate than the other models, especially in the service-based and financial sectors The research also found that the logit regression-based model (Ohlson O-Score) is superior in considering external factors, such as company size and macroeconomic conditions, compared to other models that focus more on financial ratios.
Implications & Recommendations: Any financial distress prediction model has advantages and limitations that depend on industry characteristics. Therefore, their selection should consider the financial structure, industry sector, and external factors such as regulation and economic dynamics. The integration of traditional models with machine learning and artificial intelligence (AI) is recommended to improve the accuracy and effectiveness of early detection.
Contribution & Value Added: This research provides insights for academics, practitioners, and regulators on the accuracy of financial distress prediction models and emphasizes the need for an adaptive approach that integrates financial and non-financial factors to improve business resilience