Extracción y análisis de datos públicos no estructurados disponibles en redes sociales, para la estimación de los ingresos de los clientes de una entidad bancaria
The business problem aborded in this study is the credit risk management optimization in a Bank, this will be made by increasing the reliability and precision of its client's income. In order of achieve this purpose this study will use social media features, which traditionally are not used in...
- Autores:
-
Mendoza Espinosa, Andrés Mauricio
- Tipo de recurso:
- Fecha de publicación:
- 2020
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- spa
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/51002
- Acceso en línea:
- http://hdl.handle.net/1992/51002
- Palabra clave:
- Préstamos bancarios
Riesgo crediticio
Ingreso
Redes sociales en línea
Ingeniería
- Rights
- openAccess
- License
- https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf
| Summary: | The business problem aborded in this study is the credit risk management optimization in a Bank, this will be made by increasing the reliability and precision of its client's income. In order of achieve this purpose this study will use social media features, which traditionally are not used in the credit risk problem. The main objective in this work is to determine how can a financial institution use the social media data to predict the Colombians monthly income. Considering the privacy conditions in some social media platforms, this study will be limited to the analysis of LinkedIn, El Empleo and Twitter, which are the networks with the greatest relation of income information. The question will be aborded making an analysis of public information in social media platforms, for which an effective method in data mining will be needed. After the data mining process, it will be made feature engineering, model design, results analysis, and conclusions... |
|---|