Financial Distress Prediction using Machine Learning Methods

Meghna Jain

Abstract

Bankruptcy in future would lead to heavy losses and attempt should be made to reduce it and prevent such a loss in advance. Potential Misclassification of potential and futurist bankruptcy can be referred to as an audit failure. It is important to predict bankruptcy for different users including investors, auditors, creditors, and regulators. There are various prediction models which have been considered in different studies, this research study includes various techniques like Random Forest, ANN, and Logistic Regression. The main reason behind prediction of financial distress will help in ensuring that there is increase in compatibility towards decision making process. This study is focused on analysis of 5 years data about 704 companies. In this study, 704 companies have been considered which were liquidated by NCLT since its inception i.e. 2016. Out of which 304 companies had their resolution plan approved from 2017-18 till the year 2023-24. The selected companies’ financial information has been considered for last 5 years i.e. 2018-19 to 2022-23. There are five different periods considered in the study i.e. one year, two years, three years, four years and five years. Random Forest, Artificial Neural network and Logistic Regression have been used to predict the outcome of the firm (in terms of bankruptcy or reorganization) with a certain level of accuracy