Early warning signs of financial distress using random forest and logit model

Download This Article

Valentino Budhidharma ORCID logo, Roy Sembel ORCID logo, Edison Hulu ORCID logo, Gracia Shinta S. Ugut ORCID logo

https://doi.org/10.22495/cbsrv4i4art8

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

The purpose of this study is to develop a new model to explain financial distress in Indonesia. There have been many theories, variables, and estimation methods used by previous studies about early warning signs of financial distress. Unfortunately, there are few studies on this subject using a combination of theories, random forests (RF) as the machine learning algorithm, and logit as the statistical method, especially in Indonesia. By using the RF, it is expected the study can get an improved combination of classification and regression tree (CART) and bagging (Breiman, 1996). The samples used are most sectors in Indonesia Stock Exchange (IDX) from 2005 to 2020, excluding the financial sector. The results show that cash to total assets (CTA), retained earnings to total assets (RETA), quick assets to total assets (QATA), earnings before tax to current liabilities (EBTCL), total liability to total assets (TLTA), total sales (TS), book value per share (BVPS), and market to book ratio of the firm (MB) have a negative significant association with the probability of firms in distress. While current assets to total assets (CATA), quick assets to current liabilities (QACL), total liabilities to market value of total assets (TLMTA), total assets (TA), and interest rate (INTEREST) have a positive significant association with the probability of firms in distress. In conclusion, to avoid financial distress firms must have good selling while maintaining enough cash flow to fulfill their short-term liabilities. Firms must also keep on growing to become bigger so they can withstand more crises. This condition must be supported by a conducive interest rate. Another result shows that combining theories, random forests, and logit can be used to build a new financial distress prediction model. The second result is a new enlightenment since this method can be used to develop many new financial study models, not only using logit estimates but also other estimation methods.

Keywords: Financial Distress, Random Forests, Logit

Authors’ individual contribution: Conceptualization — V.B.; Methodology — V.B.; Software — V.B.; Validation — R.S., E.H., and G.U.; Formal Analysis — R.S. and E.H.; Investigation — V.B.; Resources — V.B.; Data Curation — V.B.; Writing — Original Draft — V.B.; Writing — Review & Editing — V.B.; Visualization — R.S.; Supervision — R.S., E.H., and G.U.; Project Administration — G.U.; Funding Acquisition — G.U.

Declaration of conflicting interests: The Authors declare that there is no conflict of interest.

JEL Classification: G32

Received: 23.01.2023
Accepted: 27.09.2023
Published online: 29.09.2023

How to cite this paper: Budhidharma, V., Sembel, R., Hulu, E., & Ugut, G. (2023). Early warning signs of financial distress using random forest and logit model. Corporate & Business Strategy Review, 4(4), 69–88. https://doi.org/10.22495/cbsrv4i4art8