Market volatility : can machine learning methods enhance volatility forecasting?

• Autor(a) principal: Batista, Afonso Maria Nabeto Valentim Xavier
• Data de Publicação: 2023
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10400.14/42213
• topic: Volatility forecasting; Heterogeneous autoregressive model; Machine learning; Artificial neural networks; Long short-term memory; Gated recurrent unit; Previsão de volatilidade; Modelos heterogéneos autoregressivos; Redes neurais artificiais; Domínio/Área Científica::Ciências Sociais::Economia e Gestão

This dissertation aims to test whether the use of machine learning (ML) techniques can improve volatility forecasting accuracy. More specifically, if it can beat the best econometric model, the Heterogeneous Autoregressive model of Realized Volatility (HAR-RV). Using S&P 500 Index data from May-2007 to August-2022, the superiority of the HAR-RV was tested and attested against competing econometric models EWMA and GARCH(1,1). Next, the performance of the ML Artificial Neural Network algorithms Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) are compared to the performance of the econometric models. Five different variable sets are tested for the ML models. It is found that while both ML models are able to beat the EWMA and GARCH(1,1) models by a significant margin, the HAR-RV model still outperforms LSTM and GRU. Moreover, an analysis is conduced on the models’ predictions on the period corresponding to the Covid-19 crisis. The results did not show any evidence suggesting that ML methods have a particular advantage at predicting during high volatility events. Finally, a plausible cause that could undermine the remarkable qualities of the ML methods in the aim of volatility forecasting is discussed. It is found that the rigorous set of conditions needed to be met for the proper setup of ML models are very difficult to be met using financial data, which hinders the aptitude of ML for this purpose.