Accuracy of Financial Distress Model Prediction: The Implementation of Artificial Neural Network, Logistic Regression, and Discriminant Analysis

Abstract

The ability to predict financial failure forms an essential topic in financial research. The various models developed to predict the occurrence of Financial Distress and serve as an early warning system for the company's stakeholders before bankruptcy occurs. Enhanced accuracy of the predictions improves the ability to mitigate its adverse effect. This study aims to build Financial Distress models using Artificial Neural Network Model, Logistic Regression, and Discriminant Analysis, based on samples taken from manufacture sectors in the Indonesia Stock Exchange in the period 2015-2018. Accuracy of the three techniques in predicting Financial Distress are compared and results indicate Artificial Neural Network Model gave a better performance than the other techniques. It is crucial to consider the choice of predictor variables that determined the success of the financial distress model.