Technical analysis for profitable trading

• Autor(a) principal: Pombo, Duarte da Fonseca e Costa Lopes
• Data de Publicação: 2022
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10400.14/40751
• topic: Technical analysis; Machine learning; Logistic regression; Holding period return; Forex; Profitable; Trading; Strategy; Out-of-sample; Análise técnica; Aprendizagem máquina; Regressão logística; Retornos do período de retenção; Lucro; Investimento; Estratégia; Fora de amostra; Domínio/Área Científica::Ciências Sociais::Economia e Gestão

This dissertation contributes to the current literature regarding the effectiveness of technical analysis as a trading tool and its usefulness for holding period return predictability. Using exclusively technical analysis patterns as input features, the author shows substantial minute holding period return predictability for the EUR/USD, USD/JPY and GBP/CHF exchange rates, during some periods in the first decade of the 21st century. The implemented investment strategies are based on a rolling window of logistic regression algorithms with an adjusted decision threshold. The models’ observed predictability was capable of being materialized in an intraday technical analysis trading strategy that would’ve produced wealth out-of-sample and after transaction costs. The confidence, predictability and profitability capacity of the models appears to be declining and may no longer exist.