Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Deep Learning Enhanced Realized GARCH (2302.08002v2)

Published 16 Feb 2023 in econ.EM, cs.LG, and q-fin.CP

Abstract: We propose a new approach to volatility modeling by combining deep learning (LSTM) and realized volatility measures. This LSTM-enhanced realized GARCH framework incorporates and distills modeling advances from financial econometrics, high frequency trading data and deep learning. Bayesian inference via the Sequential Monte Carlo method is employed for statistical inference and forecasting. The new framework can jointly model the returns and realized volatility measures, has an excellent in-sample fit and superior predictive performance compared to several benchmark models, while being able to adapt well to the stylized facts in volatility. The performance of the new framework is tested using a wide range of metrics, from marginal likelihood, volatility forecasting, to tail risk forecasting and option pricing. We report on a comprehensive empirical study using 31 widely traded stock indices over a time period that includes COVID-19 pandemic.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. Torben G. Andersen and Tim Bollerslev “Answering the Skeptics: Yes, Standard Volatility Models do Provide Accurate Forecasts” Publisher: [Economics Department of the University of Pennsylvania, Wiley, Institute of Social and Economic Research, Osaka University] In International Economic Review 39.4, 1998, pp. 885–905 DOI: 10.2307/2527343
  2. “Modeling and Forecasting Realized Volatility” _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1111/1468-0262.00418 In Econometrica 71.2, 2003, pp. 579–625 DOI: 10.1111/1468-0262.00418
  3. Adam Atkins, Mahesan Niranjan and Enrico Gerding “Financial news predicts stock market volatility better than close price” Publisher: Elsevier In The Journal of Finance and Data Science 4.2, 2018, pp. 120–137
  4. Richard T Baillie, Tim Bollerslev and Hans Ole Mikkelsen “Fractionally integrated generalized autoregressive conditional heteroskedasticity” In Journal of econometrics 74.1 Elsevier, 1996, pp. 3–30
  5. “Designing Realized Kernels to Measure the ex post Variation of Equity Prices in the Presence of Noise” _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.3982/ECTA6495 In Econometrica 76.6, 2008, pp. 1481–1536 DOI: 10.3982/ECTA6495
  6. Ole E. Barndorff-Nielsen and Neil Shephard “Power and Bipower Variation with Stochastic Volatility and Jumps” In Journal of Financial Econometrics 2.1, 2004, pp. 1–37 DOI: 10.1093/jjfinec/nbh001
  7. Tim Bollerslev “Generalized autoregressive conditional heteroskedasticity” In Journal of Econometrics 31.3, 1986, pp. 307–327 DOI: 10.1016/0304-4076(86)90063-1
  8. Tim Bollerslev “Glossary to ARCH (GARCH)” In CREATES Research Paper 2008.49, 2008 DOI: 10.2139/ssrn.1263250
  9. Andrea Bucci “Realized Volatility Forecasting with Neural Networks” In Journal of Financial Econometrics 18.3, 2020, pp. 502–531 DOI: 10.1093/jjfinec/nbaa008
  10. Nicolas Chopin “A sequential particle filter method for static models” In Biometrika 89.3, 2002, pp. 539–552 DOI: 10.1093/biomet/89.3.539
  11. Bent Jesper Christensen and Morten Ørregaard Nielsen “The Effect of Long Memory in Volatility on Stock Market Fluctuations” In The Review of Economics and Statistics 89.4 The MIT Press, 2007, pp. 684–700 URL: http://www.jstor.org/stable/40043094
  12. Fulvio Corsi “A Simple Approximate Long-Memory Model of Realized Volatility” In Journal of Financial Econometrics 7.2, 2009, pp. 174–196 DOI: 10.1093/jjfinec/nbp001
  13. Pierre Del Moral, Arnaud Doucet and Ajay Jasra “An adaptive sequential Monte Carlo method for approximate Bayesian computation” In Statistics and Computing 22.5, 2012, pp. 1009–1020 DOI: 10.1007/s11222-011-9271-y
  14. Zhuanxin Ding, Clive W.J. Granger and Robert F. Engle “A long memory property of stock market returns and a new model” In Journal of Empirical Finance 1.1, 1993, pp. 83–106 DOI: https://doi.org/10.1016/0927-5398(93)90006-D
  15. Robert Engle “New frontiers for arch models” _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/jae.683 In Journal of Applied Econometrics 17.5, 2002, pp. 425–446 DOI: 10.1002/jae.683
  16. Robert F. Engle “Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation” Publisher: [Wiley, Econometric Society] In Econometrica 50.4, 1982, pp. 987–1007 DOI: 10.2307/1912773
  17. Robert F. Engle and Giampiero M. Gallo “A multiple indicators model for volatility using intra-daily data” In Journal of Econometrics 131.1, 2006, pp. 3–27 DOI: 10.1016/j.jeconom.2005.01.018
  18. Robert F. Engle, Che-Hsiung Hong and Alex Kane “Valuation of Variance Forecast with Simulated Option Markets”, Working Paper Series 3350 National Bureau of Economic Research, 1990 DOI: 10.3386/w3350
  19. Tobias Fissler and Johanna F. Ziegel “Higher order elicitability and Osband’s principle” Publisher: Institute of Mathematical Statistics In The Annals of Statistics 44.4, 2016, pp. 1680–1707 DOI: 10.1214/16-AOS1439
  20. “Bridging the gap between the distribution of realized (ECU) volatility and ARCH modelling (of the Euro): the GARCH-NIG model” _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/jae.685 In Journal of Applied Econometrics 17.5, 2002, pp. 535–548 DOI: 10.1002/jae.685
  21. “Forecasting risk via realized GARCH, incorporating the realized range” Publisher: Routledge _eprint: https://doi.org/10.1080/14697688.2015.1079641 In Quantitative Finance 16.4, 2016, pp. 501–511 DOI: 10.1080/14697688.2015.1079641
  22. Lawrence R. Glosten, Ravi Jagannathan and David E. Runkle “On the Relation between the Expected Value and the Volatility of the Nominal Excess Return on Stocks” _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1111/j.1540-6261.1993.tb05128.x In The Journal of Finance 48.5, 1993, pp. 1779–1801 DOI: 10.1111/j.1540-6261.1993.tb05128.x
  23. Ian Goodfellow, Yoshua Bengio and Aaron Courville “Deep Learning” Google-Books-ID: omivDQAAQBAJ MIT Press, 2016
  24. David Gunawan, Robert Kohn and Minh Ngoc Tran “Flexible and Robust Particle Tempering for State Space Models” In Econometrics and Statistics, 2022 DOI: 10.1016/j.ecosta.2022.09.003
  25. Peter R. Hansen and Asger Lunde “A forecast comparison of volatility models: does anything beat a GARCH(1,1)?” _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/jae.800 In Journal of Applied Econometrics 20.7, 2005, pp. 873–889 DOI: 10.1002/jae.800
  26. Peter R. Hansen, Asger Lunde and James M. Nason “The Model Confidence Set” _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.3982/ECTA5771 In Econometrica 79.2, 2011, pp. 453–497 DOI: 10.3982/ECTA5771
  27. Peter Reinhard Hansen and Zhuo Huang “Exponential GARCH Modeling With Realized Measures of Volatility” Publisher: Taylor & Francis _eprint: https://doi.org/10.1080/07350015.2015.1038543 In Journal of Business & Economic Statistics 34.2, 2016, pp. 269–287 DOI: 10.1080/07350015.2015.1038543
  28. Peter Reinhard Hansen, Zhuo Huang and Howard Howan Shek “Realized GARCH: a joint model for returns and realized measures of volatility” _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/jae.1234 In Journal of Applied Econometrics 27.6, 2012, pp. 877–906 DOI: 10.1002/jae.1234
  29. “Long Short-Term Memory” Conference Name: Neural Computation In Neural Computation 9.8, 1997, pp. 1735–1780 DOI: 10.1162/neco.1997.9.8.1735
  30. Tae Hyup Roh “Forecasting the volatility of stock price index” In Expert Systems with Applications 33.4, 2007, pp. 916–922 DOI: 10.1016/j.eswa.2006.08.001
  31. Harold Jeffreys “The Theory of Probability” Google-Books-ID: vh9Act9rtzQC OUP Oxford, 1998
  32. “Modeling returns volatility: Realized GARCH incorporating realized risk measure” In Physica A: Statistical Mechanics and its Applications 500, 2018, pp. 249–258 DOI: 10.1016/j.physa.2018.02.018
  33. “Markov Chain Monte Carlo in Practice: A Roundtable Discussion” Publisher: Taylor & Francis _eprint: https://www.tandfonline.com/doi/pdf/10.1080/00031305.1998.10480547 In The American Statistician 52.2, 1998, pp. 93–100 DOI: 10.1080/00031305.1998.10480547
  34. Robert E. Kass and Adrian E. Raftery “Bayes Factors” Publisher: Taylor & Francis _eprint: https://www.tandfonline.com/doi/pdf/10.1080/01621459.1995.10476572 In Journal of the American Statistical Association 90.430, 1995, pp. 773–795 DOI: 10.1080/01621459.1995.10476572
  35. Ha Young Kim and Chang Hyun Won “Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models” In Expert Systems with Applications 103, 2018, pp. 25–37 DOI: 10.1016/j.eswa.2018.03.002
  36. “Regression Quantiles” Publisher: [Wiley, Econometric Society] In Econometrica 46.1, 1978, pp. 33–50 DOI: 10.2307/1913643
  37. Dan Li, Adam Clements and Christopher Drovandi “Efficient Bayesian estimation for GARCH-type models via Sequential Monte Carlo” In Econometrics and Statistics 19, 2021, pp. 22–46 DOI: 10.1016/j.ecosta.2020.02.002
  38. Lily Y. Liu, Andrew J. Patton and Kevin Sheppard “Does anything beat 5-minute RV? A comparison of realized measures across multiple asset classes” 5mins RV In Journal of Econometrics 187.1, 2015, pp. 293–311
  39. Yang Liu “Novel volatility forecasting using deep learning–long short term memory recurrent neural networks” Publisher: Elsevier In Expert Systems with Applications 132, 2019, pp. 99–109
  40. Benoit Mandelbrot “The Variation of Some Other Speculative Prices” In The Journal of Business 40.4 University of Chicago Press, 1967, pp. 393–413 URL: http://www.jstor.org/stable/2351623
  41. Radford M. Neal “Annealed importance sampling” In Statistics and Computing 11.2, 2001, pp. 125–139 DOI: 10.1023/A:1008923215028
  42. Daniel B. Nelson “Conditional Heteroskedasticity in Asset Returns: A New Approach” Publisher: [Wiley, Econometric Society] In Econometrica 59.2, 1991, pp. 347–370 DOI: 10.2307/2938260
  43. Trong-Nghia Nguyen, Minh-Ngoc Tran and Robert Kohn “Recurrent conditional heteroskedasticity” _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/jae.2902 In Journal of Applied Econometrics 37.5, 2022, pp. 1031–1054 DOI: 10.1002/jae.2902
  44. Eghbal Rahimikia, Stefan Zohren and Ser-Huang Poon “Realised Volatility Forecasting: Machine Learning via Financial Word Embedding” In SSRN Electronic Journal, 2021 DOI: 10.2139/ssrn.3895272
  45. “Realising the future: forecasting with high-frequency-based volatility (HEAVY) models” _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/jae.1158 In Journal of Applied Econometrics 25.2, 2010, pp. 197–231 DOI: 10.1002/jae.1158
  46. James W. Taylor “Forecasting Value at Risk and Expected Shortfall Using a Semiparametric Approach Based on the Asymmetric Laplace Distribution” Publisher: Taylor & Francis _eprint: https://doi.org/10.1080/07350015.2017.1281815 In Journal of Business & Economic Statistics 37.1, 2019, pp. 121–133 DOI: 10.1080/07350015.2017.1281815
  47. “Realized GARCH models: Simpler is better” In Finance Research Letters 33, 2020, pp. 101221 DOI: 10.1016/j.frl.2019.06.019
  48. Frank Z. Xing, Erik Cambria and Yue Zhang “Sentiment-aware volatility forecasting” In Knowledge-Based Systems 176, 2019, pp. 68–76 DOI: 10.1016/j.knosys.2019.03.029

Summary

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

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