Deep Learning methods for Portfolio Optimization

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.