Time Series Simulation by Conditional Generative Adversarial Net
Generative Adversarial Net (GAN) has proved to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data. The conditions include both categorical and continuous variables with different auxiliary information. Our simulation studies show that CGAN has the capability to learn different types of normal and heavy-tailed distributions, as well as dependent structures of different time series. It also has the capability to generate conditional predictive distributions consistent with training data distributions. We also provide an in-depth discussion on the rationale behind GAN and the neural networks as hierarchical splines to establish a clear connection with existing statistical methods of distribution generation. In practice, CGAN has a wide range of applications in market risk and counterparty risk analysis: it can be applied to learn historical data and generate scenarios for the calculation of Value-at-Risk (VaR) and Expected Shortfall (ES), and it can also predict the movement of the market risk factors. We present a real data analysis including a backtesting to demonstrate that CGAN can outperform Historical Simulation (HS), a popular method in market risk analysis to calculate VaR. CGAN can also be applied in economic time series modeling and forecasting. In this regard, we have included an example of hypothetical shock analysis for economic models and the generation of potential CCAR scenarios by CGAN at the end of the paper.Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 90
 R.S. Tsay. Analysis of Financial Time Series. John Wiley & Sons, Inc, 2002.
 R. Luo, W. Zhang, X. Xu, and J. Wang. “A Neural Stochastic Volatility Model”. arxiv preprint arXiv:1712.00504v1, 2017.
 I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. “Generative Adversarial Nets.” Advances in Neural Information Processing Systems 27, Curran Associates, Inc., 2014, pp 2672-2680.
 W. Fedus, M. Rosca, B. Lakshminarayanan, A.M. Dai, S. Mohamed, and I. Goodfellow. “Many Paths To Equilibrium: GANs Do Not Need To Decrease a Divergence at Every Step” arXiv preprint arXiv: 1710.08446v3, 2018.
 M. Arjovsky, S. Chintala, and L. Bottou. “Wasserstein GAN.” arXiv preprint arXiv:1701.07875v3, 2017.
 I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville. “Improved Training of Wasserstein GANs.” arXiv preprint arXiv: 1704.00028, 2017.
 N. Kodali, J. Abernethy, J. Hays, Z. Kira. “On Convergence and Stability of GANs.” arXiv preprint arXiv:1705.07215, 2017.
 T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford and X. Chen. “Improve Techniques for Training GANs.” arXiv preprint arXiv 1606.03498v1, 2016.
 X. Mao, Q. Li, H. Xie, R.YK Lau, Z. Wang, and S. Paul Smolley. “Least squares generative adversarial networks.” arXiv preprint ArXiv: 1611.04076, 2016.
 Mehdi Mirza and Simon Osindero. “Conditional Generative Adversarial Nets.” arXiv preprint ArXiv:1411.1784v1, 2014.
 Global Association of Risk Professionals (GARP). 2016 Financial Risk Manager (FRM) Part II: Market Risk Measurement and Management, Fifth Edition. Pearson Education, Inc., 2016.
 Ernst & Young. “Fundamental review of the trading book (FRTB): the revised market risk capital framework and its implementations”. www.ey.com/Publication/vwLUAssets/ey-fundamental-review-of-the-trading-book/$FILE/ey-fundamental-review-of-the-trading-book.pdf. 2016
 Board of Governors of the Federal Reserve System. “Comprehensive Capital Analysis and Review 2012: Methodology and Results for Stress Scenario Projections”, www.federalreserve.gov. 2012.
 M. Lucic, K. Kurach, M. Michalski, S. Gelly, and O. Bousquet. “Are GANs Created Equal? A Large-Scale Study” arXiv preprint ArXiv: 1711.10337v3, 2018.
 Keras: The Python Deep Learning library, keras.io. Date of access: 20 Sep 2018
 H. Magus and O. Christoffer. “Feedforward neural networks with ReLU activation functions are linear splines” PhD diss., Lund University, 2017.
 R. Balestiero and R. Baraniuk. “Mad Max: Affine Spline Insights into Deep Learning” arXiv preprint ArXiv:1805.06576v5, 2018.
 Kernel Approximation. Scikit-learn v0.20.2. scikit-learn.org/stable/modules/kernel_approximation.html,2019
 Yahoo Finance. finance.yahoo.com. Date of access: 20 Aug 2018.
 A. Radford, L. Metz and Soumith Chintala. “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks” arXiv preprint ArXiv:1511.0643, 2015.
 D. Berthlot, T. Schumm, and L.Metz. “BEGAN: Boundary equilibrium GAN” arXiv preprint ArXiv: 1703.10717, 2017.
 X. Zhou, Z. Pan, G. Hu, S. Tang and C. Zhao. “Stock Market Prediction on High Frequency Data Using Generative Adversarial Nets”. Mathematical Problems in Engineering, Volume 2018, Article ID 4907423, 11 pages, 2018.
 U.S. Census Bureau. www.census.gov. Date of access: 10 Aug 2018.