{"type":"ScholarlyArticle","title":"Enhancing Stock Movement Prediction with Adversarial Training","authors":[{"name":"Fuli Feng","slug":"fuli-feng","given":"Fuli","family":"Feng","affiliation":"National University of Singapore"},{"name":"Huimin Chen","slug":"huimin-chen","given":"Huimin","family":"Chen","affiliation":"Tsinghua Unversity"},{"name":"Xiangnan He","slug":"xiangnan-he","given":"Xiangnan","family":"He","affiliation":"University of Science and Technology of China"},{"name":"Ji Ding","slug":"ji-ding","given":"Ji","family":"Ding","affiliation":"University of Illinois at Urbana-Champaign"},{"name":"Maosong Sun","slug":"maosong-sun","given":"Maosong","family":"Sun","affiliation":"Tsinghua Unversity"},{"name":"Tat-Seng Chua","slug":"tat-seng-chua","given":"Tat-Seng","family":"Chua","affiliation":"National University of Singapore"}],"abstract":"This paper contributes a new machine learning solution for stock movement prediction, which aims to predict whether the price of a stock will be up or down in the near future. The key novelty is that we propose to employ adversarial training to improve the generalization of a neural network prediction model. The rationality of adversarial training here is that the input features to stock prediction are typically based on stock price, which is essentially a stochastic variable and continuously changed with time by nature. As such, normal training with static price-based features (e.g. the close price) can easily overfit the data, being insufficient to obtain reliable models. To address this problem, we propose to add perturbations to simulate the stochasticity of price variable, and train the model to work well under small yet intentional perturbations. Extensive experiments on two real-world stock data show that our method outperforms the state-of-the-art solution [Xu and Cohen, 2018] with 3.11% relative improvements on average w.r.t. accuracy, validating the usefulness of adversarial training for stock prediction task.","doi":"10.24963/ijcai.2019/810","url":"https://ijcai.org/proceedings/2019/810","pdf":"https://ijcai.org/proceedings/2019/0810.pdf","markdown":"https://ijcai.org/proceedings/2019/810.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/810","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"AI for Improving Human Well-being","track":"AI for Improving Human Well-being","number":810,"pages":{"first":5843,"last":5849},"keywords":["Special Track on AI for Improving Human-Well Being: AI applications for Improving Human-Well Being (Special Track on AI and Human Wellbeing)"],"videos":[],"references":[{"position":1,"raw":"[Adebiyi et al., 2014] A. Adebiyi, A. Adewumi, and C. Ayo. Comparison of arima and artificial neural networks models for stock price prediction. JAM, 2014.","title":"Comparison of arima and artificial neural networks models for stock price prediction","authors":"A Adebiyi, A Adewumi, C Ayo","year":"2014","venue":"JAM","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2018a] J. Chen, C. Ngo, F. Feng, and T. Chua. Deep understanding of cooking procedure for cross-modal recipe retrieval. In MM, pages 1020-1028. ACM, 2018.","title":"Deep understanding of cooking procedure for cross-modal recipe retrieval","authors":"Chen","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2018b] L. Chen, H. Zhang, J. Xiao, W. Liu, and S. Chang. Zero-shot visual recognition using semantics- preserving adversarial embedding networks. In CVPR, pages 1043-1052, 2018.","title":"Zero-shot visual recognition using semanticspreserving adversarial embedding networks","authors":"Chen","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cho et al., 2014] K. Cho, M. Van, C. Gulcehre, et al. Learn- ing phrase representations using rnn encoder-decoder for statistical machine translation. In EMNLP, pages 1724- 1734, 2014.","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","authors":"K Cho, M Van, C Gulcehre","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chong et al., 2017] E. Chong, C. Han, and F. Park. Deep learning networks for stock market analysis and predic- tion: Methodology, data representations, and case studies. ESA, 83:187-205, 2017.","title":"Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies","authors":"E Chong, C Han, F Park","year":"2017","venue":"ESA","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dai et al., 2018] H. Dai, H. Li, T. Tian, X. Huang, L. Wang, J. Zhu, and L. Song. Adversarial attack on graph structured data. In ICML, pages 1115-1124, 2018.","title":"Adversarial attack on graph structured data","authors":"H Dai, H Li, T Tian, X Huang, L Wang, J Zhu, L Song","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Diederik and Jimmy, 2015] K. Diederik and B. Jimmy. Adam: A method for stochastic optimization. ICLR, 2015.","title":"Adam: A method for stochastic optimization","authors":"K Diederik, B Jimmy","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Edwards et al., 2007] R. Edwards, J. Magee, and C. Basset- ti. Technical analysis of stock trends. CRC press, 2007.","title":"Technical analysis of stock trends","authors":"R Edwards, J Magee, C Bassetti","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fama and French, 2012] E. F. Fama and K. R. French. Size, value, and momentum in international stock returns. JFE, 105(3):457-472, 2012.","title":"Size, value, and momentum in international stock returns","authors":"E F Fama, K R French","year":"2012","venue":"JFE","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Feng et al., 2018] F. Feng, X. He, X. Wang, C. Luo, Y. Liu, and T. Chua. Temporal relational ranking for stock predic- tion. TOIS, 2018.","title":"Temporal relational ranking for stock prediction","authors":"F Feng, X He, X Wang, C Luo, Y Liu, T Chua","year":"2018","venue":"TOIS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Feng et al., 2019] F. Feng, X. He, J. Tang, and T. Chua. Graph adversarial training: Dynamically regularizing based on graph structure. arXiv, 2019.","title":"Graph adversarial training: Dynamically regularizing based on graph structure","authors":"F Feng, X He, J Tang, T Chua","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Goodfellow et al., 2015] I.","title":null,"authors":"Goodfellow","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"Goodfellow, J. Shlens, and C. Szegedy. Explaining and harnessing adversarial exam- ples. ICLR, 2015.","title":"Explaining and harnessing adversarial examples","authors":"J Goodfellow, C Shlens, Szegedy","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Graves et al., 2013] A. Graves, A. Mohamed, and G. Hin- ton. Speech recognition with deep recurrent neural net- works. In ICASSP, pages 6645-6649. IEEE, 2013.","title":"Speech recognition with deep recurrent neural networks","authors":"A Graves, A Mohamed, G Hinton","year":"2013","venue":"ICASSP","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[He et al., 2018] X. He, Z. He, X. Du, and T. Chua. Adver- sarial personalized ranking for recommendation. In SIGIR, pages 355-364, 2018.","title":"Adversarial personalized ranking for recommendation","authors":"X He, Z He, X Du, T Chua","year":"2018","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Hochreiter and Schmidhuber, 1997] S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"S Hochreiter, J Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Hu et al., 2018] Z. Hu, W. Liu, J. Bian, X. Liu, and T. Liu. Listening to chaotic whispers: A deep learning framework for news-oriented stock trend prediction. In WSDM, pages 261-269, 2018.","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 Liu","year":"2018","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Huang et al., 2005] W. Huang, Y. Nakamori, and S. Wang. Forecasting stock market movement direction with support vector machine. COR, 32(10):2513-2522, 2005.","title":"Forecasting stock market movement direction with support vector machine","authors":"W Huang, Y Nakamori, S Wang","year":"2005","venue":"COR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[iyato et al., 2017] MT. iyato, A. M. Dai, and I. Goodfel- low. Adversarial training methods for semi-supervised text classification. ICLR, 2017.","title":"Adversarial training methods for semi-supervised text classification","authors":"Iyato","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Kurakin et al., 2017] A. Kurakin, I. Goodfellow, and S. Bengio. Adversarial machine learning at scale. ICLR, 2017.","title":"Adversarial machine learning at scale","authors":"A Kurakin, I Goodfellow, S Bengio","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Li et al., 2018] Q. Li, Y. Chen, J. Wang, Y. Chen, and H. Chen. Web media and stock markets: A survey and future directions from a big data perspective. TKDE, 30(2):381-399, 2018.","title":"Web media and stock markets: A survey and future directions from a big data perspective","authors":"Q Li, Y Chen, J Wang, Y Chen, H Chen","year":"2018","venue":"TKDE","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Lin et al., 2017] T. Lin, T. Guo, and K. Aberer. Hybrid neu- ral networks for learning the trend in time series. In IJCAI, pages 2273-2279, 2017.","title":"Hybrid neural networks for learning the trend in time series","authors":"T Lin, T Guo, K Aberer","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/316"},{"position":23,"raw":"[Musgrave, 1997] G. Musgrave. A random walk down wall street. Business Economics, 32(2):74-76, 1997.","title":"A random walk down wall street","authors":"G Musgrave","year":"1997","venue":"Business Economics","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Nelson et al., 2017] D. Nelson, A. Pereira, and R. Oliveira. Stock market's price movement prediction with lstm neu- ral networks. In IJCNN, pages 1419-1426. IEEE, 2017.","title":"Stock market's price movement prediction with lstm neural networks","authors":"D Nelson, A Pereira, R Oliveira","year":"2017","venue":"IJCNN","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Nguyen et al., 2015] T. H. Nguyen, K. Shirai, and J. Velcin. Sentiment analysis on social media for stock movement prediction. ESA, 42(24):9603-9611, 2015.","title":"Sentiment analysis on social media for stock movement prediction","authors":"T H Nguyen, K Shirai, J Velcin","year":"2015","venue":"ESA","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Qin et al., 2017] Y. Qin, D. Song, H. Cheng, W. Cheng, G. Jiang, and G. Cottrell. A dual-stage attention-based recurrent neural network for time series prediction. In IJ- CAI, pages 2627-2633, 2017.","title":"A dual-stage attention-based recurrent neural network for time series prediction","authors":"Y Qin, D Song, H Cheng, W Cheng, G Jiang, G Cottrell","year":"2017","venue":"IJ-CAI","doi":null,"url":null,"internal_url":"/proceedings/2017/366"},{"position":27,"raw":"[Rosasco et al., 2004] L. Rosasco, E. D. Vito, A. Caponnet- to, M. Piana, and A. Verri. Are loss functions all the same? Neural Computation, 16(5):1063-1076, 2004.","title":"Are loss functions all the same?","authors":"L Rosasco, E D Vito, A Caponnetto, M Piana, A Verri","year":"2004","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Szegedy et al., 2013] C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus. Intrigu- ing properties of neural networks. arXiv, 2013.","title":"Intriguing properties of neural networks","authors":"C Szegedy, W Zaremba, I Sutskever, J Bruna, D Erhan, I Goodfellow, R Fergus","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Walczak, 2001] S. Walczak. An empirical analysis of da- ta requirements for financial forecasting with neural net- works. JMIS, 17(4):203-222, 2001.","title":"An empirical analysis of data requirements for financial forecasting with neural networks","authors":"S Walczak","year":"2001","venue":"JMIS","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wu et al., 2018] L. Wu, C. Quan, C. Li, and D. Ji. Parl: Let strangers speak out what you like. In CIKM, pages 677- 686. ACM, 2018.","title":"Parl: Let strangers speak out what you like","authors":"L Wu, C Quan, C Li, D Ji","year":"2018","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Xu and Cohen, 2018] Y. Xu and S. Cohen. Stock movement prediction from tweets and historical prices. In ACL, vol- ume 1, pages 1970-1979, 2018.","title":"Stock movement prediction from tweets and historical prices","authors":"Y Xu, S Cohen","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Yang et al., 2018] X. Yang, H. Zhang, and J. Cai. Shuffle- then-assemble: Learning object-agnostic visual relation- ship features. In ECCV, pages 36-52, 2018.","title":"Shufflethen-assemble: Learning object-agnostic visual relationship features","authors":"Yang","year":"2018","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhang et al., 2017] L. Zhang, C. Aggarwal, and G. Qi. S- tock price prediction via discovering multi-frequency trad- ing patterns. In SIGKDD, pages 2141-2149. ACM, 2017.","title":"Stock price prediction via discovering multi-frequency trading patterns","authors":"L Zhang, C Aggarwal, G Qi","year":"2017","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zhang et al., 2018] X. Zhang, Y. Zhang, S. Wang, Y. Yao, B. Fang, and P. Yu. Improving stock market prediction via heterogeneous information fusion. KBS, 143:236-247, 2018.","title":"Improving stock market prediction via heterogeneous information fusion","authors":"Zhang","year":"2018","venue":"KBS","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}