Machine Learning Analysis in Predicting Bankruptcy in Companies (Case Study of Manufacturing Companies Listed on the Stock Exchange)

Abstract

This study aims to analyze bankruptcy prediction for manufacturing companies using machine learning. Financial data from manufacturing companies listed on the Indonesia Stock Exchange for the period from 2013 to 2023 are used in this study. The analytical methods employed include Long Short-Term Memory (LSTM), Support Vector Machine (SVM), Random Forest, and Extreme Gradient Boosting (XGBoost). The results of this study are expected to provide benefits to various stakeholders: manufacturing companies in identifying early signs of bankruptcy, creditors in evaluating the feasibility of extending credit, investors in making investment decisions, academics in advancing research in bankruptcy prediction, and market regulators (OJK) in enhancing the efficiency of supervision over manufacturing companies. The results indicate that SVM is effective in predicting historical data with consistent performance, while LSTM excels in handling variations and patterns in new data.