Maestría en Administración Financiera · 2025
Modelo fundamental de crecimiento en utilidades y price-to-earnings ratio, P/E, de los índices accionarios internacionales
The S&P500, a barometer of the U.S. economy, is one of the world's leading stock market indices. The price-to-earnings ratio (P/E) is a valuation measure that compares a stock's market price to its earnings per share, and is commonly used to assess whether stocks are overvalued or undervalued. Forecasting the P/E ratio is complex due to factors that can influence the ratio: interest rates, economic growth, market sentiment, and financial projections for companies, among others. In this research, two recurrent neural network models were implemented: LSTM (long short-term memory) and GRU (gated recurrent unit), as well as two machine learning models: XGBoost (extreme gradient boosting) and LigthGBM (light gradient boosting machine), to forecast the P/E ratio of the S&P500 using historical data between January 1990 and October 2024. The results show that all four models perform well, although the GRU model stands out in terms of accuracy and computational efficiency, without leaving aside the LightGBM model, a boosting algorithm, which also shows competitive results. The research offers valuable information on the use of the four models to forecast valuation ratios, and can be useful as support in investment decision making.
Texto completo 28 páginas con texto
Leer la tesis completa Ficha en el repositorio
Contenido
- 1. Introducciónp. 7
- 2. Marco teóricop. 10
- 2.1 Price-to-earnings (P/E)p. 10
- 2.2 Método tradicional de referencia Bai-Perronp. 10
- 2.3 Métodos basados en modelos de aprendizajep. 12
- 2.3.1 Redes neuronales recurrentesp. 12
- 2.3.2 Machine learning (aprendizaje automático)p. 13
- 3. Metodologíap. 17
- 3.1 Datos y preparaciónp. 17
- 3.2 Ejecución de los modelosp. 17
- 3.3 Criterio de comparaciónp. 18
- 4. Resultadosp. 19
- 5. Conclusiones y recomendacionesp. 24
- Referenciasp. 27
- Tabla 1. Estadística descriptiva de los datos de la P/E en el índice S&P500p. 7
- Tabla 2. Evaluación de los Modelos mediante el MSE y el RMSEp. 23
- Figura 1. P/E del índice S&P500 (01/01/1990-09/11-2022)p. 8
- Figura 3. Medias asociadas a cada régimen (1992-2024)p. 11
- Figura 4. Comportamiento de una RNN con cuatro capas ocultas y una salidap. 12
- Figura 5. Comparativo del método de crecimiento de los árboles de decisiónp. 15
- Figura 6. Modelo Treelitep. 16
- Figura 7. Iteraciones de entrenamiento del modelo GRU con ajustes de hiper-parámetrosp. 19
- batch_size: 32)p. 20
- Figura 9. Iteraciones de entrenamiento del modelo LSTM con ajuste de hiper-parámetrosp. 21
- batch_size: 40)p. 22
- LightGBM y su comportamiento predictivo para las siguientes veinticinco semanasp. 23