Ensemble Model of the Financial Distress Prediction in Visegrad Group Countries

Abstract

The issue of prediction of financial state, or especially the threat of the financial distress of companies, is very topical not only for the management of the companies to take the appropriate actions but also for all the stakeholders to know the financial health of the company and its possible future development. Therefore, the main aim of the paper is ensemble model creation for financial distress prediction. This model is created using the real data on more than 550,000 companies from Central Europe, which were collected from the Amadeus database. The model was trained and validated using 27 selected financial variables from 2016 to predict the financial distress statement in 2017. Five variables were selected as significant predictors in the model: current ratio, return on equity, return on assets, debt ratio, and net working capital. Then, the proposed model performance was evaluated using the values of the variables and the state of the companies in 2017 to predict financial status in 2018. The results demonstrate that the proposed hybrid model created by combining methods, namely RobustBoost, CART, and k-NN with optimised structure, achieves better prediction results than using one of the methods alone. Moreover, the ensemble model is a new technique in the Visegrad Group (V4) compared with other prediction models. The proposed model serves as a one-year-ahead prediction model and can be directly used in the practice of the companies as the universal tool for estimation of the threat of financial distress not only in Central Europe but also in other countries. The value-added of the prediction model is its interpretability and high-performance accuracy.

The Effect of Good Corporate Governance Mechanisms, Financial Ratio, and Financial Distress: A Study on Financial Companies

“…This symptom of financial distress can endanger business continuity, and it is feared that it can harm various parties. Therefore it is crucial to know the indications of financial distress that can be used as an early warning system in preventing bankruptcy in a company [4]. According to [4] which states that several things indicate financial distress, including (a) A decrease in the volume of company sales, (b) Experiencing dependence and difficulties in collecting receivables, (c) and experiencing a decrease in profits and dividends distributed (d) Experiencing a continuous decline in share prices.…”

“…Financial ratios that are often used to predict financial distress are operating cash flows [3], [4], [16]. Operating cash flow displays information about cash flows in and out of the company's operations in one period.…”

“…Then it is essential to find a predictive model to detect bankruptcy. Identifying companies with a tendency to financial distress can help stakeholders in decision-making and other interested parties [4]. Financial distress is a phenomenon that can be used as a signal before a company goes bankrupt [4].…”

“…Identifying companies with a tendency to financial distress can help stakeholders in decision-making and other interested parties [4]. Financial distress is a phenomenon that can be used as a signal before a company goes bankrupt [4]. There are two causes of financial distress.…”

Business Failure Prediction Based on a Cost-Sensitive Extreme Gradient Boosting Machine

“…Popularized ML-based business failure prediction (FDP) models includes support vector machine (SVM) [2]- [5], DT [6], [7], KNN [8], [9], naive Bayesian (NB) [10], neural networks (NNs) [11], [12]. Ensemble learning algorithms, which is a collection of solutions that aggregates multiple weak hypotheses into a stronger one, are considered as the mainstream ML-based FDP models [13], [14]. A mountain of evidence has shown the promise of ensemblebased business failure prediction models.…”