{"type":"ScholarlyArticle","title":"Financial Thought Experiment: A GAN-based Approach to Vast Robust Portfolio Selection","authors":[{"name":"Chi Seng Pun","slug":"chi-seng-pun","given":"Chi Seng","family":"Pun","affiliation":"School of Physical and Mathematical Sciences , Nanyang Technological University , Singapore"},{"name":"Lei Wang","slug":"lei-wang","given":"Lei","family":"Wang","affiliation":"School of Physical and Mathematical Sciences , Nanyang Technological University , Singapore"},{"name":"Hoi Ying Wong","slug":"hoi-ying-wong","given":"Hoi Ying","family":"Wong","affiliation":"Department of Statistics , The Chinese University of Hong Kong , Shatin , N .T. , Hong Kong"}],"abstract":"Modern day trading practice resembles a thought experiment, where investors imagine various possibilities of future stock market and invest accordingly. Generative adversarial network (GAN) is highly relevant to this trading practice in two ways. First, GAN generates synthetic data by a neural network that is technically indistinguishable from the reality, which guarantees the reasonableness of the experiment. Second, GAN generates multitudes of fake data, which implements half of the experiment. In this paper, we present a new architecture of GAN and adapt it to portfolio risk minimization problem by adding a regression network to GAN (implementing the second half of the experiment). The new architecture is termed GANr. Battling against two distinctive networks: discriminator and regressor, GANr's generator aims to simulate a stock market that is close to the reality while allow for all possible scenarios. The resulting portfolio resembles a robust portfolio with data-driven ambiguity. Our empirical studies show that GANr portfolio is more resilient to bleak financial scenarios than CLSGAN and LASSO portfolios.","doi":"10.24963/ijcai.2020/637","url":"https://ijcai.org/proceedings/2020/637","pdf":"https://ijcai.org/proceedings/2020/0637.pdf","markdown":"https://ijcai.org/proceedings/2020/637.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/637","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":637,"pages":{"first":4619,"last":4625},"keywords":["Other areas: Financial decision-support system","Foundation for AI in FinTech: Analyzing highdimentional, sequential and evolving financial data","AI for trading: AI for novel financial models","AI for risk and security: AI for financial risk analytics","AI for trading: AI for portfolio analytics"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24787/file_24787.m3u8","length_sec":301,"provider":"hls"}],"references":[{"position":1,"raw":"[Arjovsky et al., 2017] Martin Arjovsky, Soumith Chintala, and Léon Bottou. Wasserstein generative adversarial net- works. In Proceedings of the 34th International Con- ference on Machine Learning (ICML 2017), volume 70, pages 214-223. PMLR, August 2017.","title":"Wasserstein generative adversarial networks","authors":"Arjovsky","year":"2017","venue":"Proceedings of the 34th International Conference on Machine Learning (ICML 2017)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chiu et al., 2017] Mei Choi Chiu, Chi Seng Pun, and Hoi Ying Wong. Big data challenges of high-dimensional continuous-time mean-variance portfolio selection and a remedy. Risk Analysis, 37(8):1532-1549, March 2017.","title":"Big data challenges of high-dimensional continuous-time mean-variance portfolio selection and a remedy","authors":"Mei Choi Chiu, Chi Seng Pun, Hoi Ying Wong","year":"2017","venue":"Risk Analysis","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[DeMiguel et al., 2009] Victor DeMiguel, Lorenzo Gar- lappi, and Raman Uppal. Optimal versus naive diversifica- tion: How inefficient is the 1/N portfolio strategy? Review of Financial Studies, 22(5):1915-1953, December 2009.","title":"Optimal versus naive diversification: How inefficient is the 1/N portfolio strategy?","authors":"Victor Demiguel, Lorenzo Garlappi, Raman Uppal","year":"2009","venue":"Review of Financial Studies","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Fan et al., 2012] Jianqing Fan, Jingjin Zhang, and Ke Yu. Vast portfolio selection with gross-exposure con- straints. Journal of the American Statistical Association, 107(498):592-606, June 2012.","title":"Vast portfolio selection with gross-exposure constraints","authors":"Jianqing Fan, Jingjin Zhang, Ke Yu","year":"2012","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Fouque et al., 2016] Jean-Pierre Fouque, Chi Seng Pun, and Hoi Ying Wong. Portfolio optimization with ambigu- ous correlation and stochastic volatilities. SIAM Journal on Control and Optimization, 54(5):2309-2338, January 2016.","title":"Portfolio optimization with ambiguous correlation and stochastic volatilities","authors":"Jean-Pierre Fouque, Chi Seng Pun, Hoi Ying Wong","year":"2016","venue":"SIAM Journal on Control and Optimization","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gilboa and Schmeidler, 1989] Itzhak Gilboa and David Schmeidler. Maxmin expected utility with non-unique prior. Journal of Mathematical Economics, 18(2):141- 153, January 1989.","title":"Maxmin expected utility with non-unique prior","authors":"Schmeidler Gilboa, Itzhak Gilboa, David Schmeidler","year":"1989","venue":"Journal of Mathematical Economics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Goodfellow et al., 2014] Ian Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gen- erative adversarial nets. In Advances in Neural Informa- tion Processing Systems 27 (NIPS 2014), NIPS Proceed- ings, pages 2672-2680. NIPS, December 2014.","title":"Generative adversarial nets","authors":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio","year":"2014","venue":"Advances in Neural Information Processing Systems 27 (NIPS 2014), NIPS Proceedings","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hansen et al., 2006] Lars Peter Hansen, Thomas J. Sargent, Gauhar Turmuhambetova, and Noah Williams. Robust control and model misspecification. Journal of Economic Theory, 128(1):45-90, May 2006.","title":"Robust control and model misspecification","authors":"Hansen","year":"2006","venue":"Journal of Economic Theory","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Koshiyama et al., 2019] Adriano Koshiyama, Nick Firoozye, and Philip Treleaven. Generative adver- sarial networks for financial trading strategies fine-tuning and combination. arXiv:1901.01751, pages 1-17, March 2019.","title":"Generative adversarial networks for financial trading strategies fine-tuning and combination","authors":"Adriano Koshiyama, Nick Firoozye, Philip Treleaven","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Mach, 1973] Ernst Mach. On thought experiments. Philo- sophical Forum, 4(3):449-457, 1973.","title":"Ernst Mach. On thought experiments","authors":"Mach","year":"1973","venue":"Philosophical Forum","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Mao et al., 2017] Xudong Mao, Qing Li, Haoran Xie, Ray- mond Y.K. Lau, Zhen Wang, and Stephen Paul Smol- ley. Least squares generative adversarial networks. In 2017 IEEE International Conference on Computer Vision (ICCV). IEEE, October 2017.","title":"Least squares generative adversarial networks","authors":"Xudong Mao, Qing Li, Haoran Xie, Y K Raymond, Zhen Lau, Stephen Paul Wang, Smolley","year":"2017","venue":"IEEE International Conference on Computer Vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Mao et al., 2019] Xudong Mao, Qing Li, Haoran Xie, Ray- mond Yiu Keung Lau, Zhen Wang, and Stephen Paul Smolley. On the effectiveness of least squares generative adversarial networks. IEEE Transactions on Pattern Anal- ysis and Machine Intelligence, 41(12):2947-2960, De- cember 2019.","title":"On the effectiveness of least squares generative adversarial networks","authors":"Xudong Mao, Qing Li, Haoran Xie, Raymond Yiu, Keung Lau, Zhen Wang, Stephen Paul Smolley","year":"2019","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Markowitz, 1952] Harry Markowitz. Portfolio selection. The Journal of Finance, 7(1):77-91, March 1952.","title":"Portfolio selection","authors":"Markowitz","year":"1952","venue":"The Journal of Finance","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mirza and Osindero, 2014] Mehdi Mirza and Simon Osindero. Conditional generative adversarial nets. arXiv:1411.1784, pages 1-7, November 2014.","title":"Conditional generative adversarial nets","authors":"Mehdi Mirza, Simon Osindero","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Pun and Wong, 2015] Chi Seng Pun and Hoi Ying Wong. Robust investment-reinsurance optimization with multi- scale stochastic volatility. Insurance: Mathematics and Economics, 62:245-256, May 2015.","title":"Robust investment-reinsurance optimization with multiscale stochastic volatility","authors":"Wong ; ] Pun, Seng Chi, Pun, Ying Hoi, Wong","year":"2015","venue":"Insurance: Mathematics and Economics","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Pun and Wong, 2016a] Chi Seng Pun and Hoi Ying Wong. Resolution of degeneracy in Merton's portfolio problem. SIAM Journal on Financial Mathematics, 7(1):786-811, January 2016.","title":"Resolution of degeneracy in Merton's portfolio problem","authors":"Wong Pun, Seng Chi, Pun, Ying Hoi, Wong","year":"2016","venue":"SIAM Journal on Financial Mathematics","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Pun and Wong, 2016b] Chi Seng Pun and Hoi Ying Wong. Robust non-zero-sum stochastic differential reinsurance game. Insurance: Mathematics and Economics, 68:169- 177, May 2016.","title":"Robust non-zero-sum stochastic differential reinsurance game","authors":"Pun, Seng Wong ; B] Chi, Pun, Ying Hoi, Wong","year":"2016","venue":"Insurance: Mathematics and Economics","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Pun and Wong, 2019] Chi Seng Pun and Hoi Ying Wong. A linear programming model for selection of sparse high- dimensional multiperiod portfolios. European Journal of Operational Research, 273(2):754-771, March 2019.","title":"A linear programming model for selection of sparse highdimensional multiperiod portfolios","authors":"Wong ; ] Pun, Seng Chi, Pun, Ying Hoi, Wong","year":"2019","venue":"European Journal of Operational Research","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Pun et al., 2016] Chi Seng Pun, Chi Chung Siu, and Hoi Ying Wong. Non-zero-sum reinsurance games subject to ambiguous correlations. Operations Research Letters, 44(5):578-586, September 2016.","title":"Non-zero-sum reinsurance games subject to ambiguous correlations","authors":"Chi Seng Pun, Chi Chung Siu, Hoi Ying Wong","year":"2016","venue":"Operations Research Letters","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pun, 2018a] Chi Seng Pun. G-expected utility maximization with ambiguous equicorrelation. SSRN.com/abstract=3276001, pages 1-23, Decem- ber 2018.","title":"G-expected utility maximization with ambiguous equicorrelation","authors":"; Pun, Seng Chi, Pun","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Pun, 2018b] Chi Seng Pun. Low-and high-dimensional stock price data (Mendeley data, v3), May 2018.","title":"Low-and high-dimensional stock price data","authors":"Chi Pun, Seng Pun","year":"2018","venue":"Mendeley data","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Pun, 2018c] Chi Seng Pun. Robust time-inconsistent stochastic control problems. Automatica, 94:249-257, Au- gust 2018.","title":"Robust time-inconsistent stochastic control problems","authors":"Chi Pun, Seng Pun","year":"2018","venue":"Automatica","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Srivastava et al., 2014] Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdi- nov. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15:1929-1958, June 2014.","title":"Dropout: A simple way to prevent neural networks from overfitting","authors":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov","year":"2014","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Tibshirani, 1996] Robert Tibshirani. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 58(1):267- 288, January 1996.","title":"Regression shrinkage and selection via the lasso","authors":"Robert Tibshirani","year":"1996","venue":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wald, 1945] Abraham Wald. Statistical decision functions which minimize the maximum risk. The Annals of Mathe- matics, 46(2):265, April 1945.","title":"Abraham Wald. Statistical decision functions which minimize the maximum risk","authors":"Wald","year":"1945","venue":"The Annals of Mathematics","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}