Deep Learning methods for Portfolio Optimization

Bertani, Federico (2021) Deep Learning methods for Portfolio Optimization. [Laurea magistrale], Università di Bologna, Corso di Studio in Informatica [LM-DM270]
Documenti full-text disponibili:
[img] Documento PDF (Thesis)
Disponibile con Licenza: Creative Commons: Attribuzione - Condividi allo stesso modo 4.0 (CC BY-SA 4.0)

Download (3MB)

Abstract

Portfolio optimization is one of the most studied fields that have been researched with machine learning approaches because of its inherent demand for forecasting future market properties. In this thesis, it is shown how one can use deep neural networks with historical returns to do risk adjusted asset allocation. Unlike previous studies which set as target variable asset prices, the variable to predict here is represented by the best asset allocation strategy. Experiments performed on a time period of seven years show that temporal convolutional networks are superior to long short term memory networks and transformers. Compared to baseline benchmarks, the computed allocation has an average increase in the year revenue between 2% and 5%. Furthermore, results are compared against equally weighted, inverse volatility and risk parity methods, showing higher cumulative returns than the first method and equal if not higher in some cases than the latter methods.

Abstract
Tipologia del documento
Tesi di laurea (Laurea magistrale)
Autore della tesi
Bertani, Federico
Relatore della tesi
Scuola
Corso di studio
Indirizzo
CURRICULUM A: TECNICHE DEL SOFTWARE
Ordinamento Cds
DM270
Parole chiave
Deep Learning,Portfolio Optimization,Financial Markets,Asset Allocation,Temporal Convolutional Neural Networks,Short Long Term Memory Networks,Transformers,Inverse Volatility,Risk Parity
Data di discussione della Tesi
13 Ottobre 2021
URI

Altri metadati

Statistica sui download

Gestione del documento: Visualizza il documento

^