A Neuro-Structural Framework for Bankruptcy Prediction

Quantitative Finance (Forthcoming)

47 Pages Posted: 3 Jul 2023

See all articles by Christakis Charalambous

Christakis Charalambous

University of Cyprus - Department of Public and Business Administration

Spiros Martzoukos

University of Cyprus - Department of Public and Business Administration; George Washington University - School of Business

Zenon Taoushianis

University of Southampton - Department of Banking and Finance

Date Written: May 1, 2023

Abstract

We develop a framework to simultaneously compute the unobservable parameters underlying the structural-parametric models for bankruptcy prediction. More specifically, we compute the unobservable parameters such as, asset value and asset volatility, through learning by embedding in the structural models a neural network that maps the neural network’s input space (e.g., companies’ observable financial and market data) to the unobservable parameter space. Within such a “neuro-structural” framework, the neural network and the structural model work together as a one unit during the learning phase by providing to each other forward and backward information, respectively, until the weights of the neural network are optimized according to a merit function. Empirical results show that structural models, like the Black-Scholes-Merton and the Down-and-Out option models, with parameters computed with our approach, perform better than alternative specifications of the structural models, out of sample, in terms of discriminatory power, information content and economic impact. Importantly, they also perform better than a standard neural network, suggesting that the co-joint dynamics between the neural network and the structural model are useful during the learning phase and can improve the prediction performance (and the training efficiency) of neural networks. Finally, our approach provides methodological (and empirical) enhancements over logit specifications such as, Campbell et al. (2008). There, financial and market data are the inputs, and the output is the probability of bankruptcy whereas our approach includes an intermediary step to obtain the unobservable parameters and subsequently the probability of bankruptcy.

Keywords: parameters estimation, bankruptcy prediction, neuro-structural approach, economic impact, discriminatory power

JEL Classification: G33, C45, C53, C61, D87

Suggested Citation

Charalambous, Christakis and Martzoukos, Spiros Harilaos Spiridon and Taoushianis, Zenon, A Neuro-Structural Framework for Bankruptcy Prediction (May 1, 2023). Quantitative Finance (Forthcoming), Available at SSRN: https://ssrn.com/abstract=4489623 or http://dx.doi.org/10.2139/ssrn.4489623

Christakis Charalambous

University of Cyprus - Department of Public and Business Administration ( email )

75 Kallipoleos Street
P.O. Box 20537
Nicosia CY-1678
CYPRUS
00357-2-892258 (Phone)
00357-2-339063 (Fax)

Spiros Harilaos Spiridon Martzoukos

University of Cyprus - Department of Public and Business Administration ( email )

75 Kallipoleos Street
P.O. Box 20537
Nicosia CY-1678
CYPRUS
357-2-892474 (Phone)
357-2-892460 (Fax)

George Washington University - School of Business ( email )

Washington, DC 20052
United States
202-994-5996 (Phone)
202-994-5014 (Fax)

Zenon Taoushianis (Contact Author)

University of Southampton - Department of Banking and Finance ( email )

Southampton
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
54
Abstract Views
363
Rank
710,961
PlumX Metrics