Publicação
Machine learning and asset management: clustering for portfolio construction
| Resumo: | This research investigates how machine learning can be applied to portfolio management and the results of a related experimental asset allocation. Clustering aims at minimizing inter-clustering similarities, therefore translating in potentially higher diversification benefits, one of the goals of portfolio managers. The chosen allocation strategy of this research is K-Means clustering on prices with the 100 stocks with largest capitalization in the S&P500 index, fully backtested and measured as of performance. The strategy yields interesting out-of-sample explanatory power, with good results over the considered period, although confirming the difficulty for portfolio managers to consistently deliver high abnormal returns. |
|---|---|
| Autores principais: | Vialetto, Giacomo |
| Assunto: | Machine learning Asset management Clustering Portfolio |
| Ano: | 2023 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade Nova de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório Institucional da UNL |
| Resumo: | This research investigates how machine learning can be applied to portfolio management and the results of a related experimental asset allocation. Clustering aims at minimizing inter-clustering similarities, therefore translating in potentially higher diversification benefits, one of the goals of portfolio managers. The chosen allocation strategy of this research is K-Means clustering on prices with the 100 stocks with largest capitalization in the S&P500 index, fully backtested and measured as of performance. The strategy yields interesting out-of-sample explanatory power, with good results over the considered period, although confirming the difficulty for portfolio managers to consistently deliver high abnormal returns. |
|---|