A Machine learning approach for forecasting financial bubbles
The goal of this document is to categorically foresee bubble like behavior in stocks. In order to accomplish this a wide variety of libraries, including Google¿s renowned Tensorflow and a well founded and updated stock market dataset were be used. The data gathering process for this project was with...
- Autores:
-
Londoño Bohórquez, Daniel Santiago
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2022
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/58811
- Acceso en línea:
- http://hdl.handle.net/1992/58811
- Palabra clave:
- Machine Learning
Ingeniería
- Rights
- openAccess
- License
- Atribución 4.0 Internacional
| Summary: | The goal of this document is to categorically foresee bubble like behavior in stocks. In order to accomplish this a wide variety of libraries, including Google¿s renowned Tensorflow and a well founded and updated stock market dataset were be used. The data gathering process for this project was without a doubt the biggest challenge of all. This is basically due to the fact that we are studying dead companies. The 2001 Dotcom Crash forced hundreds of companies file for chapter 11, forcing their financial data to become unavailable, even in large databases such as Bloomberg¿s or the SEC¿s. The final model is optimal when it comes evaluate bubble behavior in securities. |
|---|