Giordano, Ferdinando (A.A. 2023/2024) Financial time series forecasting: an empirical analysis of Fama-French 3 factor model portfolios. Tesi di Laurea in Computational finance, Luiss Guido Carli, relatore Nicola Borri, pp. 38. [Bachelor's Degree Thesis]

PDF (Full text) Restricted to Registered users only Download (775kB) | Request a copy

Abstract/Index

Financial time series and theoretical aspects of the models proposed. Introduction to financial time series. Challenges and characteristics in financial time series forecasting. Theoretical foundations of forecasting models. Traditional time series models. Introduction to machine learning models for time series. Deep learning models for time series. Recurrent neural networks and LSTMs. Evaluation metrics for forecasting performance. The Fama-French 3 factor model. The capital asset pricing model (CAPM). Limitations of CAPM and the need for multi-factor models. The Fama-French 3 factor model. Empirical evidence and applications. Forecasting Fama-French portfolios. Data source and content. Distribution and Correlation Analysis of Portfolio Returns. ARIMA model application and results. GARCH model for volatility forecasting. Forecasting with machine learning models. XGBoost model application and results. Random forest vs GARCH for volatility forecasting. Forecasting returns with deep learning models.

References

Bibliografia: p. 34.

Thesis Type:	Bachelor's Degree Thesis
Institution:	Luiss Guido Carli
Degree Program:	Bachelor's Degree Programs > Bachelor's Degree Program in Management and Computer Science, English language (L-18)
Chair:	Computational finance
Thesis Supervisor:	Borri, Nicola
Academic Year:	2023/2024
Session:	Extraordinary
Deposited by:	Alessandro Perfetti
Date Deposited:	24 Jun 2025 14:00
Last Modified:	24 Jun 2025 14:00
URI:	https://tesi.luiss.it/id/eprint/42622

Downloads

Repository Staff Only

View Item