An Optimal Model of Financial Distress Prediction: A Comparative Study between Neural Networks and Logistic Regression
In the face of rising defaults and limited studies on the prediction of financial distress in Morocco, this article aims to determine the most relevant predictors of financial distress and identify its optimal prediction models in a normal Moroccan economic context over two years. To achieve these o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Risks |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9091/9/11/200 |
| _version_ | 1797508525440630784 |
|---|---|
| author | Youssef Zizi Amine Jamali-Alaoui Badreddine El Goumi Mohamed Oudgou Abdeslam El Moudden |
| author_facet | Youssef Zizi Amine Jamali-Alaoui Badreddine El Goumi Mohamed Oudgou Abdeslam El Moudden |
| author_sort | Youssef Zizi |
| collection | DOAJ |
| description | In the face of rising defaults and limited studies on the prediction of financial distress in Morocco, this article aims to determine the most relevant predictors of financial distress and identify its optimal prediction models in a normal Moroccan economic context over two years. To achieve these objectives, logistic regression and neural networks are used based on financial ratios selected by lasso and stepwise techniques. Our empirical results highlight the significant role of predictors, namely interest to sales and return on assets in predicting financial distress. The results show that logistic regression models obtained by stepwise selection outperform the other models with an overall accuracy of 93.33% two years before financial distress and 95.00% one year prior to financial distress. Results also show that our models classify distressed SMEs better than healthy SMEs with type I errors lower than type II errors. |
| first_indexed | 2024-03-10T05:05:09Z |
| format | Article |
| id | doaj.art-9510aa82560c41db8299230f1a50c2ff |
| institution | Directory Open Access Journal |
| issn | 2227-9091 |
| language | English |
| last_indexed | 2024-03-10T05:05:09Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Risks |
| spelling | doaj.art-9510aa82560c41db8299230f1a50c2ff2023-11-23T01:22:50ZengMDPI AGRisks2227-90912021-11-0191120010.3390/risks9110200An Optimal Model of Financial Distress Prediction: A Comparative Study between Neural Networks and Logistic RegressionYoussef Zizi0Amine Jamali-Alaoui1Badreddine El Goumi2Mohamed Oudgou3Abdeslam El Moudden4Laboratory of Research in Organizational Management Sciences, ENCG Kenitra, Ibn Tofail University, Kenitra 14000, MoroccoFaculty of Science and Technology, Sidi Mohammed Ben Abdellah University, Fez 3000, MoroccoINSA EUROMED, University EUROMED of Fez, Fez 3000, MoroccoENCG Béni Mellal, University Sultane Moulay Slimane, Béni Mellal 23000, MoroccoLaboratory of Research in Organizational Management Sciences, ENCG Kenitra, Ibn Tofail University, Kenitra 14000, MoroccoIn the face of rising defaults and limited studies on the prediction of financial distress in Morocco, this article aims to determine the most relevant predictors of financial distress and identify its optimal prediction models in a normal Moroccan economic context over two years. To achieve these objectives, logistic regression and neural networks are used based on financial ratios selected by lasso and stepwise techniques. Our empirical results highlight the significant role of predictors, namely interest to sales and return on assets in predicting financial distress. The results show that logistic regression models obtained by stepwise selection outperform the other models with an overall accuracy of 93.33% two years before financial distress and 95.00% one year prior to financial distress. Results also show that our models classify distressed SMEs better than healthy SMEs with type I errors lower than type II errors.https://www.mdpi.com/2227-9091/9/11/200financial distress predictionlogistic regressionneural networksfeature selectionSMEseconometric modeling |
| spellingShingle | Youssef Zizi Amine Jamali-Alaoui Badreddine El Goumi Mohamed Oudgou Abdeslam El Moudden An Optimal Model of Financial Distress Prediction: A Comparative Study between Neural Networks and Logistic Regression Risks financial distress prediction logistic regression neural networks feature selection SMEs econometric modeling |
| title | An Optimal Model of Financial Distress Prediction: A Comparative Study between Neural Networks and Logistic Regression |
| title_full | An Optimal Model of Financial Distress Prediction: A Comparative Study between Neural Networks and Logistic Regression |
| title_fullStr | An Optimal Model of Financial Distress Prediction: A Comparative Study between Neural Networks and Logistic Regression |
| title_full_unstemmed | An Optimal Model of Financial Distress Prediction: A Comparative Study between Neural Networks and Logistic Regression |
| title_short | An Optimal Model of Financial Distress Prediction: A Comparative Study between Neural Networks and Logistic Regression |
| title_sort | optimal model of financial distress prediction a comparative study between neural networks and logistic regression |
| topic | financial distress prediction logistic regression neural networks feature selection SMEs econometric modeling |
| url | https://www.mdpi.com/2227-9091/9/11/200 |
| work_keys_str_mv | AT youssefzizi anoptimalmodeloffinancialdistresspredictionacomparativestudybetweenneuralnetworksandlogisticregression AT aminejamalialaoui anoptimalmodeloffinancialdistresspredictionacomparativestudybetweenneuralnetworksandlogisticregression AT badreddineelgoumi anoptimalmodeloffinancialdistresspredictionacomparativestudybetweenneuralnetworksandlogisticregression AT mohamedoudgou anoptimalmodeloffinancialdistresspredictionacomparativestudybetweenneuralnetworksandlogisticregression AT abdeslamelmoudden anoptimalmodeloffinancialdistresspredictionacomparativestudybetweenneuralnetworksandlogisticregression AT youssefzizi optimalmodeloffinancialdistresspredictionacomparativestudybetweenneuralnetworksandlogisticregression AT aminejamalialaoui optimalmodeloffinancialdistresspredictionacomparativestudybetweenneuralnetworksandlogisticregression AT badreddineelgoumi optimalmodeloffinancialdistresspredictionacomparativestudybetweenneuralnetworksandlogisticregression AT mohamedoudgou optimalmodeloffinancialdistresspredictionacomparativestudybetweenneuralnetworksandlogisticregression AT abdeslamelmoudden optimalmodeloffinancialdistresspredictionacomparativestudybetweenneuralnetworksandlogisticregression |