Crunching Numbers, Making Decisions: Artificial Intelligence and Statistics for Financial Distress Forecasting in Algeria and Saudi Arabia

Abstract

Predicting financial distress has been a significant concern for both researchers and practitioners for long period. This topic has garnered substantial interest due to the potential benefits of using predictive models to anticipate financial troubles and help companies steer clear of financial risks that could lead to bankruptcy and liquidation. The primary aim of this research is to forecast financial distress, comparing the effectiveness of Artificial Neural Network (ANN) with Logistic Regression (LR). This evaluation is based on data from 12 Algerian companies and 12 Saudi companies during the period from 2015 to 2019. The study's findings indicate that the LR model outperformed the Wide Neural Network (WNN) model in accurately predicting financial distress, achieving optimal classification accuracy for both Algerian and Saudi companies. Consequently, the LR model emerges as the preferred choice for forecasting financial distress in both countries.