Predicting Financial Distress in Indonesian Companies using Machine Learning

Abstract

Predicting financial distress is essential in Indonesia's rapidly evolving economy, characterized by diverse business environments and regulatory challenges. This study evaluates four machine learning classifiers, XGBoost, Random Forest (RF), Support Vector Classification (SVC), and Long Short-Term Memory (LSTM), to predict financial distress among Indonesian companies. Two sampling methods, Random Under-Sampling (RUS) and Synthetic Minority Over-Sampling Technique (SMOTE), were used to address class imbalance. Empirical results indicate that the RF model trained with SMOTE sampling was the most effective, achieving an F1 score of 0.9632 and an accuracy of 0.96, while the XGBoost classifier with RUS sampling achieved a precision of 0.9716. These findings provide valuable insights into Indonesia's financial sector, guiding the selection of appropriate models for timely financial distress prediction and intervention.