{"type":"ScholarlyArticle","title":"A Smart Trader for Portfolio Management based on Normalizing Flows","authors":[{"name":"Mengyuan Yang","slug":"mengyuan-yang","given":"Mengyuan","family":"Yang","affiliation":"Zhejiang University , Hangzhou , China"},{"name":"Xiaolin Zheng","slug":"xiaolin-zheng","given":"Xiaolin","family":"Zheng","affiliation":"Zhejiang University , Hangzhou , China"},{"name":"Qianqiao Liang","slug":"qianqiao-liang","given":"Qianqiao","family":"Liang","affiliation":"Zhejiang University , Hangzhou , China"},{"name":"Bing Han","slug":"bing-han","given":"Bing","family":"Han","affiliation":"MYbank , Ant Group , Hangzhou , China"},{"name":"Mengying Zhu","slug":"mengying-zhu","given":"Mengying","family":"Zhu","affiliation":"Zhejiang University , Hangzhou , China"}],"abstract":"In this paper, we study a new kind of portfolio problem, named trading point aware portfolio optimization (TPPO), which aims to obtain excess intraday profit by deciding the portfolio weights and their trading points simultaneously based on microscopic information. However, a strategy for the TPPO problem faces two challenging problems, i.e., modeling the ever-changing and irregular microscopic stock price time series and deciding the scattering candidate trading points. To address these problems, we propose a novel TPPO strategy named STrader based on normalizing flows. STrader is not only promising in reversibly transforming the geometric Brownian motion process to the unobservable and complicated stochastic process of the microscopic stock price time series for modeling such series, but also has the ability to earn excess intraday profit by capturing the appropriate trading points of the portfolio. Extensive experiments conducted on three public datasets demonstrate STrader's superiority over the state-of-the-art portfolio strategies.","doi":"10.24963/ijcai.2022/557","url":"https://ijcai.org/proceedings/2022/557","pdf":"https://ijcai.org/proceedings/2022/0557.pdf","markdown":"https://ijcai.org/proceedings/2022/557.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/557","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":557,"pages":{"first":4014,"last":4021},"keywords":["Machine Learning: Time-series; Data Streams","Machine Learning: Deep Reinforcement Learning","Multidisciplinary Topics and Applications: Finance"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986967","length_sec":90,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985110","length_sec":666,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Chen et al., 2018] Ricky TQ Chen, Yulia Rubanova, Jesse Bettencourt, and David Duvenaud. Neural ordinary differ- ential equations. In Proc. of NeurIPS, pages 6572-6583, 2018.","title":"Neural ordinary differential equations","authors":"Yulia Ricky Tq Chen, Jesse Rubanova, David Bettencourt, Duvenaud","year":"2018","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ding et al., 2020] Qianggang Ding, Sifan Wu, Hao Sun, Ji- adong Guo, and Jian Guo. Hierarchical multi-scale gaus- sian transformer for stock movement prediction. In Proc. of IJCAI, pages 4640-4646, 2020.","title":"Hierarchical multi-scale gaussian transformer for stock movement prediction","authors":"Ding","year":"2020","venue":"Proc. of IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/640"},{"position":3,"raw":"[Fraccaro et al., 2016] Marco Fraccaro, Søren Kaae Sønderby, Ulrich Paquet, and Ole Winther. Sequential neural models with stochastic layers. In Proc. of NeurIPS, pages 2199-2207, 2016.","title":"Sequential neural models with stochastic layers","authors":"Marco Fraccaro, Kaae Søren, Ulrich Sønderby, Ole Paquet, Winther","year":"2016","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Grathwohl et al., 2018] Will Grathwohl, Ricky TQ Chen, Jesse Bettencourt, Ilya Sutskever, and David Duvenaud. Ffjord: Free-form continuous dynamics for scalable re- versible generative models. In Proc. of ICLR, 2018.","title":"Ffjord: Free-form continuous dynamics for scalable reversible generative models","authors":"Grathwohl","year":"2018","venue":"Proc. of ICLR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Imajo et al., 2021] Kentaro Imajo, Kentaro Minami, Kat- suya Ito, and Kei Nakagawa. Deep portfolio optimization via distributional prediction of residual factors. In Proc. of AAAI, pages 213-222, 2021.","title":"Deep portfolio optimization via distributional prediction of residual factors","authors":"Kentaro Imajo, Kentaro Minami, Katsuya Ito, Kei Nakagawa","year":"2021","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Jiang et al., 2017] Zhengyao Jiang, Dixing Xu, and Jinjun Liang. A deep reinforcement learning framework for the financial portfolio management problem. arXiv preprint arXiv:1706.10059, 2017.","title":"A deep reinforcement learning framework for the financial portfolio management problem","authors":"Jiang","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Kingma and Ba, 2014] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kingma and Dhariwal, 2018] Diederik P. Kingma and Pra- fulla Dhariwal. Glow: Generative flow with invertible 1x1 convolutions. In Proc. of NeurIPS, pages 10236-10245, 2018.","title":"Glow: Generative flow with invertible 1x1 convolutions","authors":"P Diederik, Prafulla Kingma, Dhariwal","year":"2018","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Li and Arora, 2019] Zhiyuan Li and Sanjeev Arora. An ex- ponential learning rate schedule for deep learning. arXiv preprint arXiv:1910.07454, 2019.","title":"An exponential learning rate schedule for deep learning","authors":"Li, Arora, Zhiyuan Li, Sanjeev Arora","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Li and Hoi, 2014] Bin Li and Steven C. H. Hoi. Online portfolio selection: a survey. ACM Computing Surveys, 87(2):1-36, 2014.","title":"Online portfolio selection: a survey","authors":"Hoi ; ] Bin Li, Steven C H Li, Hoi","year":"2014","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Li et al., 2020] Xuechen Li, Ting-Kam Leonard Wong, Ricky TQ Chen, and David Duvenaud. Scalable gradients for stochastic differential equations. In Proc. of AISTATS, pages 3870-3882, 2020.","title":"Scalable gradients for stochastic differential equations","authors":"Li","year":"2020","venue":"Proc. of AISTATS","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liang et al., 2021] Qianqiao Liang, Mengying Zhu, Xi- aolin Zheng, and Yan Wang. An adaptive news-driven method for cvar-sensitive online portfolio selection in non- stationary financial markets. In Proc. of IJCAI, pages 2708-2715, 2021.","title":"An adaptive news-driven method for cvar-sensitive online portfolio selection in nonstationary financial markets","authors":"Qianqiao Liang, Mengying Zhu, Xiaolin Zheng, Yan Wang","year":"2021","venue":"Proc. of IJCAI","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2019] Shikun Liu, Edward Johns, and Andrew J Davison. End-to-end multi-task learning with attention. In Proc. of CVPR, pages 1871-1880, 2019.","title":"End-to-end multi-task learning with attention","authors":"Shikun Liu, Edward Johns, Andrew J Davison","year":"2019","venue":"Proc. of CVPR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu et al., 2020] Guang Liu, Yuzhao Mao, Qi Sun, Hailong Huang, Weiguo Gao, Xuan Li, Jianping Shen, Ruifan Li, and Xiaojie Wang. Multi-scale two-way deep neural net- work for stock trend prediction. In Proc. of IJCAI, pages 4555-4561, 2020.","title":"Multi-scale two-way deep neural network for stock trend prediction","authors":"Guang Liu, Yuzhao Mao, Qi Sun, Hailong Huang, Weiguo Gao, Xuan Li, Jianping Shen, Ruifan Li, Xiaojie Wang","year":"2020","venue":"Proc. of IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/628"},{"position":15,"raw":"[Luo et al., 2018] Rui Luo, Weinan Zhang, Xiaojun Xu, and Jun Wang. A neural stochastic volatility model. In Proc. of AAAI, pages 6401-6408, 2018.","title":"A neural stochastic volatility model","authors":"Rui Luo, Weinan Zhang, Xiaojun Xu, Jun Wang","year":"2018","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Marathe and Ryan, 2005] Rahul R Marathe and Sarah M Ryan. On the validity of the geometric brownian motion assumption. The Engineering Economist, 50(2):159-192, 2005.","title":"On the validity of the geometric brownian motion assumption","authors":"R Rahul, Sarah M Marathe, Ryan","year":"2005","venue":"The Engineering Economist","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Moody and Saffell, 2001] John Moody and Matthew Saf- fell. Learning to trade via direct reinforcement. IEEE Transactions on Neural Networks, 12(4):875-889, 2001.","title":"John Moody and Matthew Saffell. Learning to trade via direct reinforcement","authors":"Saffell Moody","year":"2001","venue":"IEEE Transactions on Neural Networks","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Oksendal, 2013] Bernt Oksendal. Stochastic differential equations: an introduction with applications. Springer Science & Business Media, 2013.","title":"Stochastic differential equations: an introduction with applications","authors":"Bernt Oksendal","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Rezende and Mohamed, 2015] Danilo Jimenez Rezende and Shakir Mohamed. Variational inference with nor- malizing flows. In Proc. of ICML, pages 1530-1538, 2015.","title":"Variational inference with normalizing flows","authors":"Mohamed ; Rezende, Danilo Jimenez, Rezende, Shakir Mohamed","year":"2015","venue":"Proc. of ICML","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Rubanova et al., 2019] Yulia Rubanova, Tian Qi Chen, and David Duvenaud. Latent ordinary differential equations for irregularly-sampled time series. In Proc. of NeurIPS, pages 5321-5331, 2019.","title":"Latent ordinary differential equations for irregularly-sampled time series","authors":"Yulia Rubanova, Tian Qi Chen, David Duvenaud","year":"2019","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Shi et al., 2019] Si Shi, Jianjun Li, Guohui Li, and Peng Pan. A multi-scale temporal feature aggregation convolu- tional neural network for portfolio management. In Proc. of CIKM, pages 1613-1622, 2019.","title":"A multi-scale temporal feature aggregation convolutional neural network for portfolio management","authors":"Si Shi, Jianjun Li, Guohui Li, Peng Pan","year":"2019","venue":"Proc. of CIKM","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Veličković et al., 2017] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.","title":"Graph attention networks","authors":"Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2021] Zhicheng Wang, Biwei Huang, Shikui Tu, Kun Zhang, and Lei Xu. Deeptrader: A deep rein- forcement learning approach for risk-return balanced port- folio management with market conditions embedding. In Proc. of AAAI, pages 643-650, 2021.","title":"Deeptrader: A deep reinforcement learning approach for risk-return balanced portfolio management with market conditions embedding","authors":"Zhicheng Wang, Biwei Huang, Shikui Tu, Kun Zhang, Lei Xu","year":"2021","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xu et al., 2020] Ke Xu, Yifan Zhang, Deheng Ye, Peilin Zhao, and Mingkui Tan. Relation-aware transformer for portfolio policy learning. In Proc. of IJCAI, pages 4647- 4653, 2020.","title":"Relation-aware transformer for portfolio policy learning","authors":"Ke Xu, Yifan Zhang, Deheng Ye, Peilin Zhao, Mingkui Tan","year":"2020","venue":"Proc. of IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/641"},{"position":25,"raw":"[Ye et al., 2020] Yunan Ye, Hengzhi Pei, Boxin Wang, Pin- Yu Chen, Yada Zhu, Ju Xiao, and Bo Li. Reinforcement- learning based portfolio management with augmented as- set movement prediction states. In Proc. of AAAI, pages 1112-1119, 2020.","title":"Reinforcementlearning based portfolio management with augmented asset movement prediction states","authors":"Yunan Ye, Hengzhi Pei, Boxin Wang, Pin-Yu Chen, Yada Zhu, Ju Xiao, Bo Li","year":"2020","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yor, 2001] Marc Yor. Exponential functionals of Brownian motion and related processes, volume 112. Springer, 2001.","title":"Exponential functionals of Brownian motion and related processes","authors":"Marc Yor","year":"2001","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang et al., 2022] Yifan Zhang, Peilin Zhao, Qingyao Wu, Bin Li, Junzhou Huang, and Mingkui Tan. Cost- sensitive portfolio selection via deep reinforcement learn- ing. IEEE Transactions on Knowledge and Data Engineer- ing, 34(1):236-248, 2022.","title":"Costsensitive portfolio selection via deep reinforcement learning","authors":"Yifan Zhang, Peilin Zhao, Qingyao Wu, Bin Li, Junzhou Huang, Mingkui Tan","year":"2022","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhu et al., 2020] Mengying Zhu, Xiaolin Zheng, Yan Wang, Qianqiao Liang, and Wenfang Zhang. Online port- folio selection with cardinality constraint and transaction costs based on contextual bandit. In Proc. of IJCAI, pages 4682-4689, 2020.","title":"Online portfolio selection with cardinality constraint and transaction costs based on contextual bandit","authors":"Mengying Zhu, Xiaolin Zheng, Yan Wang, Qianqiao Liang, Wenfang Zhang","year":"2020","venue":"Proc. of IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/646"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}