A machine learning approach for banks classification and forecast
n this research, a classification model is developed for the banking sector using the machine earning technique GLMNET. In the first place, a clustering process was developed, where 3 clearly differentiated groups were found. Subsequently, a Fuzzy analysis was performed finding the probabilities of...
- Autores:
-
Fontalvo Herrera, Tomas
De La Hoz Dominguez, Enrique
- Tipo de recurso:
- Fecha de publicación:
- 2019
- Institución:
- Universidad Tecnológica de Bolívar
- Repositorio:
- Repositorio Institucional UTB
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.utb.edu.co:20.500.12585/12096
- Acceso en línea:
- https://hdl.handle.net/20.500.12585/12096
- Palabra clave:
- Customer Churn;
Sales;
Customer Relationship Management
LEMB
- Rights
- openAccess
- License
- http://creativecommons.org/licenses/by-nc-nd/4.0/
| Summary: | n this research, a classification model is developed for the banking sector using the machine earning technique GLMNET. In the first place, a clustering process was developed, where 3 clearly differentiated groups were found. Subsequently, a Fuzzy analysis was performed finding the probabilities of transition of the banks to each group found, finally, the GLMNET algorithm was implemented, the automatic classification of the banks according to their financial items, obtaining a result of 95% accuracy. © 2019 International Business Information Management Association (IBIMA). |
|---|