This book investigates the application of promising machine learning techniques to address two problems: (i) how to find profitable pairs while constraining the search space and (ii) how to avoid long decline periods due to prolonged divergent pairs. It also proposes the integration of an unsupervised learning algorithm, OPTICS, to handle problem (i), and demonstrates that the suggested technique can outperform the common pairs search methods, achieving an average portfolio Sharpe ratio of 3.79, in comparison to 3.58 and 2.59 obtained using standard approaches. For problem (ii), the authors introduce a forecasting-based trading model capable of reducing the periods of portfolio decline by 75%. However, this comes at the expense of decreasing overall profitability. The authors also test the proposed strategy using an ARMA model, an LSTM and an LSTM encoder-decoder.
Introduction.- Pairs Trading - Background and Related Work.- Proposed Pairs Selection Framework.- Proposed Trading Model.- Implementation.- Results.- Conclusions and Future Work.
Sim?o Sarmento received his B.Sc. and M.Sc. degrees in Electrical and Computer Engineering from the Instituto Superior T?cnico (IST), University of Lisbon, Portugal, in 2017 and 2019, respectively. In 2018, he completed the first year of his masters degree at the Ecole Polytechnique F?d?rale de Lausanne (EPFL), Lausanne, Switzerland, where he focused on machine learning. He also worked at the Research and Development Department of Feedzai from July to September 2018, investigating the application of deep learning to fight financial fraud.
Nuno Horta (S89M97SM11) received his Licenciado, M.Sc., Ph.D. and Postdoctorate degrees in Electrical and Computer Engineer from the Instituto Supel“É
![A Machine Learning based Pairs Trading Investment Strategy [Paperback]](/itemImage/2/2/8/0/2_4492882.jpg "A Machine Learning based Pairs Trading Investment Strategy [Paperback]")