The present paper aims to compare the predictive performance of five models namely the Linear Discriminant Analysis (LDA), Logistic Regression (LR), Decision Trees (DT), Support Vector Machine (SVM) and Random Forest (RF) to forecast the bankruptcy of Tunisian companies. A Deep Neural Network (DNN) model is also applied to conduct a prediction performance comparison with other statistical and machine learning algorithms. The data used for this empirical investigation covers 25 financial ratios for a large sample of 732 Tunisian companies from 2011–2017. To interpret the prediction results, three performance measures have been employed; the accuracy percentage, the F1 score, and the Area Under Curve (AUC). In conclusion, DNN shows higher accuracy in predicting bankruptcy compared to other conventional models, whereas the random forest performs better than other machine learning and statistical methods.

The aim of this paper is to compare the model of logistic regression versus logistic regression with random effects in order to predict the credit risk of Tunisian banks. To do this, a battery of 26 ratios was calculated from balance sheets and income statements of 528 Tunisian firms from different sectors of activities for the fiscal years 1999–2006. By using information about the activity sector of each firms, we applied the logistic regression model with random effects to take into account the presence of unobserved heterogeneity. The obtained results show that the integration of sectoral effect improves the quality of model predictions in terms of good classification as well as by the ROC curve results.

Objectif: L’objectif de cet article est de mettre en évidence l'efficacité du modèle GARCH non paramétrique pour la prédiction des prix futurs du Bitcoin. Méthodologie: Les modèles GARCH paramétriques pour caractériser la volatilité des rendements Bitcoin sont très utilisés dans la littérature empirique. Alternativement, nous considérons une approche non paramétrique pour modéliser et prévoir la volatilité des rendements Bitcoin. Résultats: Nous montrons que la prévision de volatilité du modèle GARCH non paramétrique donne des performances supérieures par rapport à une classe étendue de modèles GARCH paramétriques. Originalité/pertinence : L’amélioration de la précision des prévisions de la volatilité des rendements Bitcoin basée sur le modèle GARCH non paramétrique suggère que cette méthode offre une alternative attrayante et viable par rapport aux modèles paramétriques GARCH couramment utilisés.

Over the past few years, the financial sector has witnessed an increase in the adoption of machine learning models within banking and insurance domains. Advanced analytic teams in the financial community are implementing these models regularly. This paper aims to explore the various machine learning approaches utilized in these sectors and offers recommendations for selecting suitable methods for financial applications. Additionally, the paper provides references to R packages that can be used to compute the machine learning methods. Our aim is to bring a valuable contribution to the field of financial research by providing a more comprehensive and advanced method of credit scoring, which in turn improves assessments of customers' debt repayment capabilities and improves risk management tactics.© 2024 The Author(s). Published by RITHA Publishing. This article is distributed under the terms of the license CC-BY 4.0., which permits any further distribution in any medium, provided the original work is properly cited.

In the last years, the financial sector has seen an increase in the use of machine learning models in banking and insurance contexts. Advanced analytic teams in the financial community are implementing these models regularly. In this paper, i present the different Machine Learning techniques used, and provide some suggestions on the choice of methods in financial applications. We refer the reader to the R packages that can be used to compute the Machine learning methods.