{"type":"ScholarlyArticle","title":"WATTNet: Learning to Trade FX via Hierarchical Spatio-Temporal Representation of Highly Multivariate Time Series","authors":[{"name":"Michael Poli","slug":"michael-poli","given":"Michael","family":"Poli","affiliation":"Department of Industrial & Systems Engineering , KAIST , Daejeon , South Korea; Neuri Pte Ltd , Singapore , Singapore"},{"name":"Jinkyoo Park","slug":"jinkyoo-park","given":"Jinkyoo","family":"Park","affiliation":"Department of Industrial & Systems Engineering , KAIST , Daejeon , South Korea"},{"name":"Ilija Ilievski","slug":"ilija-ilievski","given":"Ilija","family":"Ilievski","affiliation":"Neuri Pte Ltd , Singapore , Singapore"}],"abstract":"Finance is a particularly challenging application area for deep learning models due to low noise-to-signal ratio, non-stationarity, and partial observability. Non-deliverable-forwards (NDF), a derivatives contract used in foreign exchange (FX) trading, presents additional difficulty in the form of long-term planning required for an effective selection of start and end date of the contract. In this work, we focus on tackling the problem of NDF position length selection by leveraging high-dimensional sequential data consisting of spot rates, technical indicators and expert tenor patterns. To this end, we curate, analyze and release a dataset from the Depository Trust & Clearing Corporation (DTCC) NDF data that includes a comprehensive list of NDF volumes and daily spot rates for 64 FX pairs. We introduce WaveATTentionNet (WATTNet), a novel temporal convolution (TCN) model for spatio-temporal modeling of highly multivariate time series, and validate it across NDF markets with varying degrees of dissimilarity between the training and test periods in terms of volatility and general market regimes. The proposed method achieves a significant positive return on investment (ROI) in all NDF markets under analysis, outperforming recurrent and classical baselines by a wide margin. Finally, we propose two orthogonal interpretability approaches to verify noise robustness and detect the driving factors of the learned tenor selection strategy.","doi":"10.24963/ijcai.2020/630","url":"https://ijcai.org/proceedings/2020/630","pdf":"https://ijcai.org/proceedings/2020/0630.pdf","markdown":"https://ijcai.org/proceedings/2020/630.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/630","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Special Track on AI in FinTech","track":"Special Track on AI in FinTech","number":630,"pages":{"first":4569,"last":4575},"keywords":["AI for trading: AI for algorithmic trading","Other areas: Interpretability of FinTech","Foundation for AI in FinTech: Deep learning and representation for FinTech","Foundation for AI in FinTech: Analyzing highdimentional, sequential and evolving financial data"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24168/file_24168.m3u8","length_sec":275,"provider":"hls"}],"references":[{"position":1,"raw":"[Baehrens et al., 2010] Baehrens, D.; Schroeter, T.; Harmel- ing, S.; Kawanabe, M.; Hansen, K.; and M Þller, K.-R. 2010. How to explain individual classification decisions. Journal of Machine Learning Research 11(Jun):1803- 1831.","title":"How to explain individual classification decisions","authors":"D Baehrens, T Schroeter, S Harmeling, M Kawanabe, K Hansen, K.-R Þller","year":"2010","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Carapuc ¸o, Neves, and Horta, 2018] Carapuc ¸o, J.; Neves, R.; and Horta, N. 2018. Reinforcement learning applied to forex trading. Applied Soft Computing 73:783-794.","title":"Reinforcement learning applied to forex trading","authors":"J Carapuc ¸o, R Neves, N Horta","year":"2018","venue":"Applied Soft Computing","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chan and Teong, 1995] Chan, K. C., and Teong, F. K. 1995. Enhancing technical analysis in the forex mar- ket using neural networks. In Proceedings of ICNN'95- International Conference on Neural Networks, volume 2, 1023-1027. IEEE.","title":"Enhancing technical analysis in the forex market using neural networks","authors":"K C Chan, F K Teong","year":"1995","venue":"Proceedings of ICNN'95-International Conference on Neural Networks","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Czekalski, Niezabitowski, and Styblinski, 2015] Czekalski, P.; Niezabitowski, M.; and Styblinski, R. 2015. Ann for forex forecasting and trading. In 2015 20th International Conference on Control Systems and Computer Science, 322-328. IEEE.","title":"Ann for forex forecasting and trading","authors":"P Czekalski, M Niezabitowski, R Styblinski","year":"2015","venue":"20th International Conference on Control Systems and Computer Science","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Galeshchuk and Mukherjee, 2017] Galeshchuk, S., and Mukherjee, S. 2017. Deep networks for predicting direction of change in foreign exchange rates. Intelli- gent Systems in Accounting, Finance and Management 24(4):100-110.","title":"Deep networks for predicting direction of change in foreign exchange rates","authors":"S Galeshchuk, S Mukherjee","year":"2017","venue":"Intelligent Systems in Accounting, Finance and Management","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Guhr and Kälber, 2003] Guhr, T., and Kälber, B. 2003. A new method to estimate the noise in financial correlation matrices. Journal of Physics A: Mathematical and General 36(12):3009.","title":"A new method to estimate the noise in financial correlation matrices","authors":"T Guhr, B Kälber","year":"2003","venue":"Journal of Physics A: Mathematical and General","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hu et al., 2018] Hu, Z.; Liu, W.; Bian, J.; Liu, X.; and Liu, T.-Y. 2018. Listening to chaotic whispers: A deep learn- ing framework for news-oriented stock trend prediction. In Proceedings of the Eleventh ACM International Con- ference on Web Search and Data Mining, 261-269. ACM.","title":"Listening to chaotic whispers: A deep learning framework for news-oriented stock trend prediction","authors":"Z Hu, W Liu, J Bian, X Liu, T.-Y Liu","year":"2018","venue":"Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Judah, Fern, and Dietterich, 2012] Judah, K.; Fern, A. P.; and Dietterich, T. G. 2012. Active imitation learning via reduction to iid active learning. In 2012 AAAI Fall Sympo- sium Series.","title":"Active imitation learning via reduction to iid active learning","authors":"Fern Judah, ; ] Dietterich, K Judah, A P Fern, T G Dietterich","year":"2012","venue":"AAAI Fall Symposium Series","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kingma and Ba, 2015] Kingma, D. P., and Ba, J. 2015. Adam: A method for stochastic optimization. In 3rd Inter- national Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.","title":"Adam: A method for stochastic optimization","authors":"D P Kingma, J Ba","year":"2015","venue":"3rd International Conference on Learning Representations, ICLR 2015","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lai et al., 2018] Lai, G.; Chang, W.-C.; Yang, Y.; and Liu, H. 2018. Modeling long-and short-term temporal patterns with deep neural networks. In The 41st International ACM SIGIR Conference on Research & Development in Infor- mation Retrieval, 95-104. ACM.","title":"Modeling long-and short-term temporal patterns with deep neural networks","authors":"G Lai, W.-C Chang, Y Yang, H Liu","year":"2018","venue":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[McInnes, Healy, and Melville, 2018] McInnes, L.; Healy, J.; and Melville, J. 2018. Umap: Uniform manifold ap- proximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426.","title":"Umap: Uniform manifold approximation and projection for dimension reduction","authors":"L Mcinnes, J Healy, J Melville","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Mishra et al., 2017] Mishra, N.; Rohaninejad, M.; Chen, X.; and Abbeel, P. 2017. A simple neural attentive meta- learner. arXiv preprint arXiv:1707.03141.","title":"A simple neural attentive metalearner","authors":"N Mishra, M Rohaninejad, X Chen, P Abbeel","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Nassirtoussi et al., 2015] Nassirtoussi, A. K.; Aghabozorgi, S.; Wah, T. Y.; and Ngo, D. C. L. 2015. Text mining of news-headlines for forex market prediction: A multi- layer dimension reduction algorithm with semantics and sentiment. Expert Systems with Applications 42(1):306- 324.","title":"Text mining of news-headlines for forex market prediction: A multilayer dimension reduction algorithm with semantics and sentiment","authors":"Nassirtoussi","year":"2015","venue":"Expert Systems with Applications","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ntakaris et al., 2019] Ntakaris, A.; Mirone, G.; Kanniainen, J.; Gabbouj, M.; and Iosifidis, A. 2019. Feature engi- neering for mid-price prediction with deep learning. IEEE Access 7:82390-82412.","title":"Feature engineering for mid-price prediction with deep learning","authors":"A Ntakaris, G Mirone, J Kanniainen, M Gabbouj, A Iosifidis","year":"2019","venue":"IEEE Access","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Oord et al., 2016] Oord, A. v. d.; Dieleman, S.; Zen, H.; Simonyan, K.; Vinyals, O.; Graves, A.; Kalchbrenner, N.; Senior, A.; and Kavukcuoglu, K. 2016. Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499.","title":"Wavenet: A generative model for raw audio","authors":"A V D Oord, S Dieleman, H Zen, K Simonyan, O Vinyals, A Graves, N Kalchbrenner, A Senior, K Kavukcuoglu","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Pathberiya, Tilakaratne, and Hansen, 2017] Pathberiya, H. A.; Tilakaratne, C. D.; and Hansen, L. 2017. An intelligent system for forex trading: Hybrid ann with garch and intrinsic mode functions. In 2017 Intelligent Systems Conference (IntelliSys), 436-445. IEEE.","title":"An intelligent system for forex trading: Hybrid ann with garch and intrinsic mode functions","authors":"H A Pathberiya, C D Tilakaratne, L Hansen","year":"2017","venue":"2017 Intelligent Systems Conference (IntelliSys)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Petropoulos et al., 2017] Petropoulos, A.; Chatzis, S. P.; Siakoulis, V.; and Vlachogiannakis, N. 2017. A stacked generalization system for automated forex portfolio trad- ing. Expert Systems with Applications 90:290-302.","title":"A stacked generalization system for automated forex portfolio trading","authors":"A Petropoulos, S P Chatzis, V Siakoulis, N Vlachogiannakis","year":"2017","venue":"Expert Systems with Applications","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Santoro et al., 2018] Santoro, A.; Faulkner, R.; Raposo, D.; Rae, J.; Chrzanowski, M.; Weber, T.; Wierstra, D.; Vinyals, O.; Pascanu, R.; and Lillicrap, T. 2018. Rela- tional recurrent neural networks. In Advances in Neural Information Processing Systems, 7299-7310.","title":"Relational recurrent neural networks","authors":"A Santoro, R Faulkner, D Raposo, J Rae, M Chrzanowski, T Weber, D Wierstra, O Vinyals, R Pascanu, T Lillicrap","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sornmayura, 2019] Sornmayura, S. 2019. Robust forex trading with deep q network (dqn). ABAC Journal 39(1).","title":"Robust forex trading with deep q network (dqn)","authors":"S Sornmayura","year":"2019","venue":"ABAC Journal","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Vargas, De Lima, and Evsukoff, 2017] Vargas, M. R.; De Lima, B. S.; and Evsukoff, A. G. 2017. Deep learning for stock market prediction from financial news articles. In 2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA), 60-65. IEEE.","title":"Deep learning for stock market prediction from financial news articles","authors":"M R Vargas, B S De Lima, A G Evsukoff","year":"2017","venue":"IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Vaswani et al., 2017] Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, Ł.; and Polosukhin, I. 2017. Attention is all you need. In Advances in neural information processing systems, 5998-6008.","title":"Attention is all you need","authors":"A Vaswani, N Shazeer, N Parmar, J Uszkoreit, L Jones, A N Gomez, Ł Kaiser, I Polosukhin","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wu et al., 2019] Wu, Z.; Pan, S.; Long, G.; Jiang, J.; and Zhang, C. 2019. Graph wavenet for deep spatial-temporal graph modeling. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, 1907-1913. International Joint Conferences on Artificial Intelligence Organization. [Xingjian et al., 2015]","title":"Graph wavenet for deep spatial-temporal graph modeling","authors":"Z Wu, S Pan, G Long, J Jiang, C Zhang","year":"1907","venue":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19","doi":null,"url":null,"internal_url":"/proceedings/2019/264"},{"position":23,"raw":"Xingjian, S.; Chen, Z.; Wang, H.; Ye- ung, D.-Y.; Wong, W.-K.; and Woo, W.-c. 2015. Convo- lutional lstm network: A machine learning approach for precipitation nowcasting. In Advances in neural informa- tion processing systems, 802-810.","title":"Convolutional lstm network: A machine learning approach for precipitation nowcasting","authors":"S Xingjian, Z Chen, H Wang, D.-Y Yeung, W.-K Wong, W.-C Woo","year":"2015","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yu et al., 2019] Yu, P.; Lee, J. S.; Kulyatin, I.; Shi, Z.; and Dasgupta, S. 2019. Model-based deep reinforce- ment learning for dynamic portfolio optimization. arXiv preprint arXiv:1901.08740.","title":"Model-based deep reinforcement learning for dynamic portfolio optimization","authors":"P Yu, J S Lee, I Kulyatin, Z Shi, S Dasgupta","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}