Papers
Topics
Authors
Recent
2000 character limit reached

SpotV2Net: Multivariate Intraday Spot Volatility Forecasting via Vol-of-Vol-Informed Graph Attention Networks (2401.06249v4)

Published 11 Jan 2024 in q-fin.ST and q-fin.CP

Abstract: This paper introduces SpotV2Net, a multivariate intraday spot volatility forecasting model based on a Graph Attention Network architecture. SpotV2Net represents assets as nodes within a graph and includes non-parametric high-frequency Fourier estimates of the spot volatility and co-volatility as node features. Further, it incorporates Fourier estimates of the spot volatility of volatility and co-volatility of volatility as features for node edges, to capture spillover effects. We test the forecasting accuracy of SpotV2Net in an extensive empirical exercise, conducted with the components of the Dow Jones Industrial Average index. The results we obtain suggest that SpotV2Net yields statistically significant gains in forecasting accuracy, for both single-step and multi-step forecasts, compared to a panel heterogenous auto-regressive model and alternative machine-learning models. To interpret the forecasts produced by SpotV2Net, we employ GNNExplainer \citep{ying2019gnnexplainer}, a model-agnostic interpretability tool, and thereby uncover subgraphs that are critical to a node's predictions.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (117)
  1. Volatility and correlation forecasting, Handbook of economic forecasting 1: 777–878.
  2. The distribution of realized stock return volatility, Journal of financial economics 61(1): 43–76.
  3. Realized volatility forecasting and option pricing, Journal of Econometrics 147(1): 34–46.
  4. Multivariate garch models: a survey, Journal of applied econometrics 21(1): 79–109.
  5. Selecting volatility forecasting models for portfolio allocation purposes, International Journal of Forecasting 31(3): 849–861.
  6. A capital asset pricing model with time-varying covariances, Journal of political Economy 96(1): 116–131.
  7. High-dimensional multivariate realized volatility estimation, Journal of Econometrics 212(1): 116–136.
  8. An evaluation of volatility forecasting techniques, Journal of Banking & Finance 20(3): 419–438.
  9. Cart, Classification and regression trees .
  10. Bucci, A. (2020). Realized volatility forecasting with neural networks, Journal of Financial Econometrics 18(3): 502–531.
  11. Combining multivariate volatility forecasts: an economic-based approach, Journal of Financial Econometrics 15(2): 247–285.
  12. A comparison of machine learning methods for predicting the direction of the us stock market on the basis of volatility indices, International Journal of Forecasting .
  13. Forecasting volatility with time-varying leverage and volatility of volatility effects, International Journal of Forecasting 36(4): 1301–1317.
  14. Deep learning in asset pricing, Management Science .
  15. Multivariate realized volatility forecasting with graph neural network, Proceedings of the Third ACM International Conference on AI in Finance, pp. 156–164.
  16. Volatility-of-volatility risk in asset pricing, The Review of Asset Pricing Studies 12(1): 289–335.
  17. Xgboost: A scalable tree boosting system, Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785–794.
  18. Financial time series forecasting with multi-modality graph neural network, Pattern Recognition 121: 108218.
  19. Modeling the momentum spillover effect for stock prediction via attribute-driven graph attention networks, Proceedings of the AAAI conference on artificial intelligence, Vol. 35, pp. 55–62.
  20. Volatility of volatility and leverage effect from options, arXiv preprint arXiv:2305.04137 .
  21. How relevant is volatility forecasting for financial risk management?, Review of Economics and Statistics 82(1): 12–22.
  22. Corsi, F. (2009). A simple approximate long-memory model of realized volatility, Journal of Financial Econometrics 7(2): 174–196.
  23. Convolutional neural networks on graphs with fast localized spectral filtering, Advances in neural information processing systems 29.
  24. Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting, Proceedings of the AAAI conference on artificial intelligence, Vol. 33, pp. 890–897.
  25. Ding, Y. D. (2023). A simple joint model for returns, volatility and volatility of volatility, Journal of Econometrics 232(2): 521–543.
  26. A long memory property of stock market returns and a new model, Journal of empirical finance 1(1): 83–106.
  27. Cryptocurrency volatility forecasting using commonality in intraday volatility, Proceedings of the Fourth ACM International Conference on AI in Finance, pp. 436–444.
  28. Multivariate simultaneous generalized arch, Econometric theory 11(1): 122–150.
  29. Forecasting intraday volatility in the us equity market. multiplicative component garch, Journal of Financial Econometrics 10(1): 54–83.
  30. Graph neural networks for social recommendation, The world wide web conference, pp. 417–426.
  31. Intraday price discovery and volatility spillovers in an emerging market, International Review of Economics and Finance 59: 333–346.
  32. Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine, Annals of statistics pp. 1189–1232.
  33. Applying lstm to time series predictable through time-window approaches, International conference on artificial neural networks, Springer, pp. 669–676.
  34. The estimation and application of long memory time series models, Journal of time series analysis 4(4): 221–238.
  35. High-frequency trading strategies, Management Science 69: 4413–4434.
  36. Intra-daily volatility spillovers in international stock markets, Journal of International Money and Finance 53: 95–114.
  37. Deep learning, MIT press.
  38. Discovering supply chain links with augmented intelligence, arXiv preprint arXiv:2111.01878 .
  39. An introduction to long-memory time series models and fractional differencing, Journal of time series analysis 1(1): 15–29.
  40. Empirical asset pricing via machine learning, The Review of Financial Studies 33(5): 2223–2273.
  41. Inductive representation learning on large graphs, Advances in neural information processing systems 30.
  42. Deep learning for finance: deep portfolios, Applied Stochastic Models in Business and Industry 33(1): 3–12.
  43. The common factor in idiosyncratic volatility: Quantitative asset pricing implications, Journal of Financial Economics 119(2): 249–283.
  44. Firm volatility in granular networks, Journal of Political Economy 128(11): 4097–4162.
  45. Long short-term memory, Neural computation 9(8): 1735–1780.
  46. Volatility-of-volatility risk, Journal of Financial and Quantitative Analysis 54(6): 2423–2452.
  47. Mixgcf: An improved training method for graph neural network-based recommender systems, Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 665–674.
  48. Forecasting realised volatility using arfima and har models, Quantitative Finance 19(10): 1627–1638.
  49. Statistical properties of microstructure noise, Econometrica 85(4): 1133–1174.
  50. Perceiver: General perception with iterative attention, International conference on machine learning, PMLR, pp. 4651–4664.
  51. Intraday bidirectional volatility spillover across international stock markets: does the global financial crisis matter?, Applied Economics 47: 3633–3650.
  52. Graph neural network for traffic forecasting: A survey, Expert Systems with Applications 207: 117921.
  53. High-frequency volatility co-movements in cryptocurrency markets, Journal of International Financial Markets, Institutions and Money 62: 35–52.
  54. Hats: A hierarchical graph attention network for stock movement prediction, arXiv preprint arXiv:1908.07999 .
  55. Semi-supervised classification with graph convolutional networks, arXiv preprint arXiv:1609.02907 .
  56. Convolutional networks for images, speech, and time series, The handbook of brain theory and neural networks 3361(10): 1995.
  57. Li, L. (2022). The dynamic interrelations of oil-equity implied volatility indexes under low and high volatility-of-volatility risk, Energy Economics 105: 105756.
  58. Spatial-temporal fusion graph neural networks for traffic flow forecasting, Proceedings of the AAAI conference on artificial intelligence, Vol. 35, pp. 4189–4196.
  59. Volatility of volatility: Estimation and tests based on noisy high frequency data with jumps, Journal of Econometrics 229(2): 422–451.
  60. Intraday volatility smile: Effects of fragmentation and high-frequency trading on price efficiency, Journal of International Financial Markets, Institutions and Money 75: 101437.
  61. Portfolio selection under non-gaussianity and systemic risk: A machine learning based forecasting approach, International Journal of Forecasting .
  62. Forecasting and trading high-frequency volatility on large indices, Quantitative Finance 18: 737–748.
  63. Preventing attacks in interbank credit rating with selective-aware graph neural network, Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, pp. 6085–6093.
  64. Liu, Y. (2019). Novel volatility forecasting using deep learning–long short term memory recurrent neural networks, Expert Systems with Applications 132: 99–109.
  65. Portfolio optimization with return prediction using deep learning and machine learning, Expert Systems with Applications 165: 113973.
  66. Rectifier nonlinearities improve neural network acoustic models, Proc. icml, Vol. 30, Atlanta, GA, p. 3.
  67. Intraday portfolio risk management using var and cvar:a cgarch-evt-copula approach, International Journal of Forecasting 35: 699–709.
  68. Fourier series method for measurement of multivariate volatilities, Finance and Stochastics 6(1): 49–61.
  69. A fourier transform method for nonparametric estimation of multivariate volatility, The Annals of Statistics 37(4): 1983–2010.
  70. Asymptotic normality for the fourier spot volatility estimator in the presence of microstructure noise, arXiv preprint arXiv:2209.08967 .
  71. Fourier spot volatility estimator: asymptotic normality and efficiency with liquid and illiquid high-frequency data, PloS one 10(9): e0139041.
  72. Fourier-Malliavin Volatility Estimation: theory and practice, Springer.
  73. Estimating Covariance via Fourier Method in the Presence of Asynchronous Trading and Microstructure Noise, Journal of Financial Econometrics 9(2): 367–408.
  74. From zero-intelligence to queue-reactive: limit-order-book modeling for high-frequency volatility estimation and optimal execution, Quantitative Finance 23(3): 367–388.
  75. Quantitative risk management: Concepts, techniques and tools, Princeton University Press .
  76. Menghani, G. (2023). Efficient deep learning: A survey on making deep learning models smaller, faster, and better, ACM Computing Surveys 55(12): 1–37.
  77. Stgsn—a spatial–temporal graph neural network framework for time-evolving social networks, Knowledge-Based Systems 214: 106746.
  78. Graph neural networks for modeling causality in international trade, The international FLAIRS conference proceedings, Vol. 34.
  79. Covid-induced sentiment and the intraday volatility spillovers between energy and other etfs, Energy Economics 122: 106677.
  80. The intraday volatility spillover index approach and an application in the brexit vote, Journal of International Financial Markets, Institutions and Money 55: 241–253.
  81. Bilateral trade modelling with graph neural networks, ICLR Workshop on Practical ML for Developing Countries.
  82. Forecasting volatility in financial markets: A review, Journal of economic literature 41(2): 478–539.
  83. Harnet: A convolutional neural network for realized volatility forecasting, arXiv preprint arXiv:2205.07719 .
  84. Forecasting value at risk with intra-day return curves, International Journal of Forecasting 36: 1023–1038.
  85. Long memory and periodicity in intraday volatility, Journal of Financial Econometrics 13(4): 922–961.
  86. Learning internal representations by error propagation.
  87. High-frequency volatility of volatility estimation free from spot volatility estimates, Quantitative Finance 15(8): 1331–1345.
  88. Forecasting volatility in the financial markets, Elsevier.
  89. The graph neural network model, IEEE transactions on neural networks 20(1): 61–80.
  90. An edge feature aware heterogeneous graph neural network model to support tax evasion detection, Expert Systems with Applications 213: 118903.
  91. Tabular data: Deep learning is not all you need, Information Fusion 81: 84–90.
  92. The performance of lstm and bilstm in forecasting time series, 2019 IEEE International conference on big data (Big Data), IEEE, pp. 3285–3292.
  93. The incremental volatility information in one million foreign exchange quotations, Journal of Empirical Finance 4(4): 317–340.
  94. Toscano, G. (2022). The price-leverage covariation as a measure of the response of the leverage effect to price and volatility changes, Applied Stochastic Models in Business and Industry 38(3): 497–511.
  95. Volatility of Volatility Estimation: Central Limit Theorems for the Fourier Transform Estimator and Empirical Study of the Daily Time Series Stylized Facts*, Journal of Financial Econometrics p. nbac035.
  96. Combining long memory and level shifts in modelling and forecasting the volatility of asset returns, Quantitative Finance 18(3): 371–393.
  97. Attention is all you need, Advances in neural information processing systems 30.
  98. Graph attention networks, arXiv preprint arXiv:1710.10903 .
  99. A review on graph neural network methods in financial applications, arXiv preprint arXiv:2111.15367 .
  100. Multivariate volatility forecasts for stock market indices, International Journal of Forecasting 37(2): 484–499.
  101. Equity2vec: End-to-end deep learning framework for cross-sectional asset pricing, Proceedings of the Second ACM International Conference on AI in Finance, pp. 1–9.
  102. A comprehensive survey on graph neural networks, IEEE transactions on neural networks and learning systems 32(1): 4–24.
  103. Connecting the dots: Multivariate time series forecasting with graph neural networks, Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pp. 753–763.
  104. Multi-behavior graph neural networks for recommender system, IEEE Transactions on Neural Networks and Learning Systems .
  105. Deep learning stock volatility with google domestic trends, arXiv preprint arXiv:1512.04916 .
  106. How powerful are graph neural networks?, arXiv preprint arXiv:1810.00826 .
  107. Trading frequency and volatility clustering, Journal of Banking and Finance 36: 760–773.
  108. Graph convolutional neural networks for web-scale recommender systems, Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pp. 974–983.
  109. Time-aware graph relational attention network for stock recommendation, Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 2281–2284.
  110. Gnnexplainer: Generating explanations for graph neural networks, Advances in neural information processing systems 32.
  111. Graph neural networks for forecasting realized volatility with nonlinear spillover effects, Available at SSRN .
  112. Volatility forecasting with machine learning and intraday commonality, Journal of Financial Econometrics .
  113. Research on graph neural network in stock market, Procedia Computer Science 214: 786–792.
  114. Deep learning for portfolio optimization, The Journal of Financial Data Science .
  115. Combining intra-risk and contagion risk for enterprise bankruptcy prediction using graph neural networks, arXiv preprint arXiv:2202.03874 .
  116. Graph neural networks: A review of methods and applications, AI open 1: 57–81.
  117. Forecasting realized volatility with machine learning: Panel data perspective, Journal of Empirical Finance 73: 251–271.

Summary

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

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

Whiteboard

Open Problems

We found no open problems mentioned in this paper.

Continue Learning

We haven't generated follow-up questions for this paper yet.

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

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Tweets

Sign up for free to view the 6 tweets with 17 likes about this paper.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up for Free