Home

Deep learning in finance: Prediction of stock returns with long short-term memory networks

Year
2018
Secondary
https://storage.googleapis.com/public-quant/integrate/papers/Deep%20learning%20in%20finance_%20Prediction%20of%20stock%20returns%20with%20long%20short-term%20memory%20networks.pdf
Download
https://mega.co.nz/#!WbBQVK4Z!Rmw8aWtpoCKB2oW3hQxxz1v-15fKbbMpsD8_uQcDI3M
Abstract
1. Yijun Zhao 1. is an assistant professor of computer and information sciences and the Director of the Master of Science in Data Science program at Fordham University in New York, NY. (yzhao11{at}fordham.edu) 2. Shengjian Xu 1. is a student in the Master of Science in Data Science program at Fordham University in New York, NY. (sxu108{at}fordham.edu) 3. Jacek Ossowski 1. is an associate teaching professor of computer science in the Schaefer School of Engineering at the Stevens Institute of Technology in Hoboken, NJ. (jossowsk{at}stevens.edu) In this article, the authors study the utility of deep-learning approaches in statistical arbitrage under the generalized pairs-trading paradigm. Stock returns are regressed on a set of risk factors derived using principal component analysis, and the long short-term memory (LSTM) structure is employed to forecast directions of idiosyncratic residuals. Daily market-neutral trades are constructed based on the predicted signals. The authors compare their results with the influential relative value (RV) model by [Avellaneda and Lee (2010)][1] on the universe of S&P 500 Index (S&P 500) stocks. Model evaluations are performed on two distinct periods (2001–2007 and 2015–2021) to alleviate the survivorship bias resulting from the S&P 500 composition changes over time and to study the robustness of these two models in two distinct eras. Their findings suggest that the LSTM model consistently and significantly outperforms the
Author
Miquel N. Alonso and Gilberto Batres-Estrada and Aymeric Moulin
View
https://sci-hub.st/10.1002/9781119522225.ch13
Journal
https://books.google.com/books?hl=en&lr=&id=5et1DwAAQBAJ&oi=fnd&pg=PA251&dq=Deep+Learning+Meets+Statistical+Arbitrage:+An+Application+of+Long+Short-Term+Memory+Networks+to+Algorithmic+Trading&ots=0fDZ-0eaOH&sig=-PQ133mmg9mcggSO4sdWtCKIwqk
Published
2022/09/07
Retrieved
2022/09/07 17:45
DOI
10.1002/9781119522225.ch13
TOP