Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Comparing Deep Learning Models for the Task of Volatility Prediction Using Multivariate Data (2306.12446v2)

Published 20 Jun 2023 in q-fin.ST, cs.LG, q-fin.CP, and q-fin.RM

Abstract: This study aims to compare multiple deep learning-based forecasters for the task of predicting volatility using multivariate data. The paper evaluates a range of models, starting from simpler and shallower ones and progressing to deeper and more complex architectures. Additionally, the performance of these models is compared against naive predictions and variations of classical GARCH models. The prediction of volatility for five assets, namely S&P500, NASDAQ100, gold, silver, and oil, is specifically addressed using GARCH models, Multi-Layer Perceptrons, Recurrent Neural Networks, Temporal Convolutional Networks, and the Temporal Fusion Transformer. In the majority of cases, the Temporal Fusion Transformer, followed by variants of the Temporal Convolutional Network, outperformed classical approaches and shallow networks. These experiments were repeated, and the differences observed between the competing models were found to be statistically significant, thus providing strong encouragement for their practical application.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (74)
  1. Hans-Martin Adorf and Mark D. Johnston. 1990. A discrete stochastic neural network algorithm for constraint satisfaction problems. In 1990 IJCNN International Joint Conference on Neural Networks. IEEE, 917–924 vol.3. https://doi.org/10.1109/IJCNN.1990.137951
  2. Torben G. Andersen and Tim Bollerslev. 1998. Answering the Skeptics: Yes, Standard Volatility Models do Provide Accurate Forecasts. International Economic Review 39, 4 (Nov. 1998), 885. https://doi.org/10.2307/2527343
  3. Layer Normalization. In Advances in NIPS 2016 Deep Learning Symposium. https://arxiv.org/abs/1607.06450v1
  4. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. (April 2018). http://arxiv.org/abs/1803.01271
  5. Christopher Bishop. 2006. Pattern Recognition and Machine Learning. Springer-Verlag, New York. https://www.springer.com/gp/book/9780387310732
  6. Tim Bollerslev. 1986. Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics 31, 3 (April 1986), 307–327. https://doi.org/10.1016/0304-4076(86)90063-1
  7. Language Models are Few-Shot Learners. Advances in Neural Information Processing Systems 33 (2020), 1877–1901. https://papers.nips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html
  8. Andrea Bucci. 2020. Cholesky–ANN models for predicting multivariate realized volatility. Journal of Forecasting 39, 6 (2020), 865–876. https://doi.org/10.1002/for.2664
  9. Duality between Time Series and Networks. PLOS ONE 6, 8 (Aug. 2011), e23378. https://doi.org/10.1371/journal.pone.0023378
  10. Computational Intelligence and Financial Markets: A Survey and Future Directions. Expert Systems with Applications 55 (Aug. 2016), 194–211. https://doi.org/10.1016/j.eswa.2016.02.006
  11. Volatility forecasting using deep neural network with time-series feature embedding. Economic Research-Ekonomska Istraživanja (2022), 1–25.
  12. Tommy W. S. Chow and Chi-Tat Leung. 1996. Neural network based short-term load forecasting using weather compensation. IEEE Transactions on Power Systems 11, 4 (Nov. 1996), 1736–1742. https://doi.org/10.1109/59.544636
  13. Monetary Policy Rules and Macroeconomic Stability: Evidence and Some Theory. The Quarterly Journal of Economics 115, 1 (2000), 147–180. https://www.jstor.org/stable/2586937
  14. It Pays to Follow the Leader: Acquiring Targets Picked by Private Equity. The Journal of Financial and Quantitative Analysis 47, 5 (2012), 901–931. https://www.jstor.org/stable/23351940
  15. Stock market cycles, financial liberalization and volatility. Journal of International Money and Finance 22, 7 (Dec. 2003), 925–955. https://doi.org/10.1016/j.jimonfin.2003.09.011
  16. Robert F. Engle. 1982. Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation. Econometrica 50, 4 (July 1982), 987–1008. https://doi.org/10.2307/1912773
  17. Robert F. Engle and Andrew J. Patton. 2007. 2 - What good is a volatility model?*. In Forecasting Volatility in the Financial Markets (Third Edition), John Knight and Stephen Satchell (Eds.). Butterworth-Heinemann, Oxford, 47–63. https://doi.org/10.1016/B978-075066942-9.50004-2
  18. Samuel Tabot Enow. 2023. Modelling and Forecasting volatility in International financial markets. International Journal of Research in Business and Social Science (2147-4478) 12, 2 (2023), 197–203.
  19. Neural Network–Based Financial Volatility Forecasting: A Systematic Review. Comput. Surveys 55, 1 (Jan. 2022), 14:1–14:30. https://doi.org/10.1145/3483596
  20. From the bird’s eye to the microscope: A survey of new stylized facts of the intra-daily foreign exchange markets. Finance and Stochastics 1, 2 (April 1997), 95–129. https://doi.org/10.1007/s007800050018
  21. Improving DWT-RNN model via B-spline wavelet multiresolution to forecast a high-frequency time series. Expert Systems with Applications 138 (Dec. 2019), 112842. https://doi.org/10.1016/j.eswa.2019.112842
  22. Peter R. Hansen and Asger Lunde. 2005. A forecast comparison of volatility models: does anything beat a GARCH(1,1)? Journal of Applied Econometrics 20, 7 (2005), 873–889. https://doi.org/10.1002/jae.800
  23. Mingyu Hao and Artem Lensky. 2023. Short-Term Volatility Prediction Using Deep CNNs Trained on Order Flow. arXiv:2304.02472
  24. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770–778. https://doi.org/10.1109/CVPR.2016.90 ISSN: 1063-6919.
  25. Multilayer feedforward networks are universal approximators. Neural Networks 2, 5 (Jan. 1989), 359–366. https://doi.org/10.1016/0893-6080(89)90020-8
  26. Music Transformer. arXiv:1809.04281 [cs, eess, stat] (Dec. 2018). http://arxiv.org/abs/1809.04281
  27. Deep learning for time series classification: a review. Data Mining and Knowledge Discovery 33, 4 (July 2019), 917–963. https://doi.org/10.1007/s10618-019-00619-1
  28. Ha Young Kim and Chang Hyun Won. 2018. Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models. Expert Systems with Applications 103 (Aug. 2018), 25–37. https://doi.org/10.1016/j.eswa.2018.03.002
  29. Stock Price Forecasting via Sentiment Analysis on Twitter. In Proceedings of the 20th Pan-Hellenic Conference on Informatics (PCI ’16). Association for Computing Machinery, New York, NY, USA, 1–6. https://doi.org/10.1145/3003733.3003787
  30. Werner Kristjanpoller and Esteban Hernández. 2017. Volatility of main metals forecasted by a hybrid ANN-GARCH model with regressors. Expert Systems with Applications 84 (Oct. 2017), 290–300. https://doi.org/10.1016/j.eswa.2017.05.024
  31. William H. Kruskal and W. Allen Wallis. 1952. Use of Ranks in One-Criterion Variance Analysis. J. Amer. Statist. Assoc. 47, 260 (1952), 583–621. https://doi.org/10.2307/2280779
  32. Hemanth Kumar P. and S. Basavaraj Patil. 2015. Estimation forecasting of volatility using ARIMA, ARFIMA and Neural Network based techniques. In 2015 IEEE International Advance Computing Conference (IACC). IEEE, 992–997. https://doi.org/10.1109/IADCC.2015.7154853
  33. Josef Lakonishok and Inmoo Lee. 2001. Are Insider Trades Informative? The Review of Financial Studies 14, 1 (Jan. 2001), 79–111. https://doi.org/10.1093/rfs/14.1.79
  34. Alan S. Lapedes and Robert Farber. 1987. Nonlinear signal processing using neural networks: Prediction and system modelling. In IEEE international conference on neural networks. 52. https://www.osti.gov/biblio/5470451
  35. On the Relationship between Classical Grid Search and Probabilistic Roadmaps. The International Journal of Robotics Research 23, 7-8 (Aug. 2004), 673–692. https://doi.org/10.1177/0278364904045481
  36. Temporal Convolutional Networks for Action Segmentation and Detection. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Honolulu, HI, 1003–1012. https://doi.org/10.1109/CVPR.2017.113
  37. Deep Neural Networks as Gaussian Processes. In Sixth International Conference on Learning Representations (ICLR). 17. http://arxiv.org/abs/1711.00165
  38. Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc. https://proceedings.neurips.cc/paper/2019/hash/6775a0635c302542da2c32aa19d86be0-Abstract.html
  39. Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting. arXiv:1912.09363 [cs, stat] (Sept. 2020). http://arxiv.org/abs/1912.09363
  40. Learning long-term dependencies in NARX recurrent neural networks. IEEE Transactions on Neural Networks 7, 6 (Nov. 1996), 1329–1338. https://doi.org/10.1109/72.548162
  41. Modeling the Effect of Cascading Stop-Losses and Its Impact on Price Dynamics. In AI for Financial Institutions. AAAI Bridge 2023 FinST.
  42. Farooq Malik. 2011. Estimating the impact of good news on stock market volatility. Applied Financial Economics 21, 8 (April 2011), 545–554. https://doi.org/10.1080/09603107.2010.534063
  43. Burton G. Malkiel. 1989. Efficient Market Hypothesis. In Finance, John Eatwell, Murray Milgate, and Peter Newman (Eds.). Palgrave Macmillan UK, London, 127–134. https://doi.org/10.1007/978-1-349-20213-3_13
  44. Philippe Masset. 2011. Volatility Stylized Facts. SSRN Scholarly Paper ID 1804070. Social Science Research Network, Rochester, NY. https://doi.org/10.2139/ssrn.1804070
  45. Stewart Mayhew. 1995. Implied Volatility. Financial Analysts Journal 51, 4 (1995), 8–20. https://doi.org/10.2469/faj.v51.n4.1916
  46. Efficient market hypothesis in emerging stock markets: gradual shifts and common factors in panel data. Applied Economics Letters (2023), 1–7.
  47. Mimicking insider trades. Journal of Corporate Finance 68 (June 2021), 101940. https://doi.org/10.1016/j.jcorpfin.2021.101940
  48. The impact of microblogging data for stock market prediction: Using Twitter to predict returns, volatility, trading volume and survey sentiment indices. Expert Systems with Applications 73 (May 2017), 125–144. https://doi.org/10.1016/j.eswa.2016.12.036
  49. WaveNet: A Generative Model for Raw Audio. arXiv:1609.03499 [cs] (Sept. 2016). http://arxiv.org/abs/1609.03499
  50. Mehmet Orhan and Bülent Köksal. 2012. A comparison of GARCH models for VaR estimation. Expert Systems with Applications 39, 3 (Feb. 2012), 3582–3592. https://doi.org/10.1016/j.eswa.2011.09.048
  51. A. Pandey and D. Wang. 2019. TCNN: Temporal Convolutional Neural Network for Real-time Speech Enhancement in the Time Domain. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 6875–6879. https://doi.org/10.1109/ICASSP.2019.8683634 ISSN: 2379-190X.
  52. On the difficulty of training recurrent neural networks. In Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28 (ICML’13). JMLR.org, Atlanta, GA, USA, III–1310–III–1318.
  53. Andrew J. Patton. 2011. Volatility forecast comparison using imperfect volatility proxies. Journal of Econometrics 160, 1 (Jan. 2011), 246–256. https://doi.org/10.1016/j.jeconom.2010.03.034
  54. Ser-Huang Poon and Clive W J Granger. 2003. Forecasting Volatility in Financial Markets: A Review. Journal of Economic Literature 41, 2 (2003), 478–539.
  55. Forecasting Stock Market Movement Direction Using Sentiment Analysis and Support Vector Machine. IEEE Systems Journal 13, 1 (March 2019), 760–770. https://doi.org/10.1109/JSYST.2018.2794462
  56. News Aware Volatility Forecasting: Is the Content of News Important? In Data Mining and Analytics 2007: Proceedings of the Sixth Australasian Data Mining Conference (AusDM ’07), J. Li, P. Kennedy, P. Christen, G. Williams, and I. Kolyshkina (Eds.). Australian Computer Society Inc, Australia, 157–166. http://dl.acm.org/citation.cfm?id=1378267
  57. Sebastian Ruder. 2016. An overview of gradient descent optimization algorithms. arXiv:1609.04747 [cs] (Sept. 2016). http://arxiv.org/abs/1609.04747
  58. S. S. Shapiro and M. B. Wilk. 1965. An analysis of variance test for normality (complete samples). Biometrika 52, 3-4 (Dec. 1965), 591–611. https://doi.org/10.1093/biomet/52.3-4.591 Publisher: Oxford University Press (OUP).
  59. Continual Learning with Deep Generative Replay. In Advances in Neural Information Processing Systems 30, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.). Curran Associates, Inc., 2990–2999. http://papers.nips.cc/paper/6892-continual-learning-with-deep-generative-replay.pdf
  60. Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556 [cs] (April 2015). http://arxiv.org/abs/1409.1556 arXiv: 1409.1556.
  61. Student. 1908. The probable error of a mean. Biometrika (1908), 1–25. Publisher: JSTOR.
  62. Allan Timmermann and Clive W. J. Granger. 2004. Efficient market hypothesis and forecasting. International Journal of Forecasting 20, 1 (Jan. 2004), 15–27. https://doi.org/10.1016/S0169-2070(03)00012-8
  63. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17). Curran Associates Inc., Red Hook, NY, USA, 6000–6010.
  64. Gizem Vergili and Mehmet Sinan Çelik. 2023. The Relationship Between the Indices of Volatility (VIX) and Sustainability (DJSEMUP): An ARDL Approach. Business and Economics Research Journal 14, 1 (2023), 19–29.
  65. Andrés Vidal and Werner Kristjanpoller. 2020. Gold volatility prediction using a CNN-LSTM approach. Expert Systems with Applications 157 (Nov. 2020), 113481. https://doi.org/10.1016/j.eswa.2020.113481
  66. Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting. Electronics 8, 8 (Aug. 2019), 876. https://doi.org/10.3390/electronics8080876
  67. Zhiguang Wang and Tim Oates. 2015. Encoding Time Series as Images for Visual Inspection and Classification Using Tiled Convolutional Neural Networks. In Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence. 8.
  68. Halbert White. 1990. Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings. Neural Networks 3, 5 (Jan. 1990), 535–549. https://doi.org/10.1016/0893-6080(90)90004-5
  69. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. In Adv. Neural Inf. Process. Syst., Vol. 34. Virtual Conference, 22419–22430.
  70. Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Case. arXiv:2001.08317 [cs, stat] (Jan. 2020). http://arxiv.org/abs/2001.08317
  71. Graph Neural Networks for Forecasting Multivariate Realized Volatility with Spillover Effects. arXiv:https://ssrn.com/abstract=4375165 http://dx.doi.org/10.2139/ssrn.4375165
  72. Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity. In International Conference on Learning Representations. 21. https://openreview.net/forum?id=BJgnXpVYwS
  73. Exploiting investors social network for stock prediction in China’s market. Journal of Computational Science 28 (Sept. 2018), 294–303. https://doi.org/10.1016/j.jocs.2017.10.013
  74. Time Series Analysis Based on Informer Algorithms: A Survey. Symmetry 15, 4 (2023). https://doi.org/10.3390/sym15040951
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets