{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T13:49:56Z","timestamp":1791380996742,"version":"4.3.3"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.uspto.gov\/ip-policy\/copyright-policy\/copyright-basics"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Accurate realized volatility (RV) forecasting is important for risk management and portfolio allocation, yet existing models typically capture either temporal dynamics within individual assets or a single form of cross-asset dependence. This study proposes HyGNN-RV, a hybrid graph neural network that jointly learns nonlinear temporal patterns and cross-asset volatility interdependencies. Daily, weekly, and monthly RV and the jump component each define a separate asset-relation graph, and relation-level attention learns how much each relation contributes. A parallel graph convolutional path preserves the current volatility level, which attention-based aggregation tends to smooth away, and the two paths are combined through an RV-conditioned gate. Sliding-window experiments on Dow Jones Industrial Average constituents from July 2014 to June 2025 compare HyGNN-RV with econometric, deep-learning, and graph-based benchmarks. The proposed model attains the lowest mean squared error(MSE) and quasi-likelihood loss(QLIKE), reducing the losses of the second-best model by approximately 9.9% and 3.4%, and ranks first in all six windows under QLIKE, including the COVID-19 and tariff-shock periods. The two graph paths prove complementary: removing either degrades a different error metric. Out-of-sample relation weights further show that the model shifts toward the daily relation as market volatility rises and selectively toward the jump relation during discontinuous shocks.<\/jats:p>","DOI":"10.2139\/ssrn.7576359","type":"posted-content","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T12:46:59Z","timestamp":1791377219000},"source":"Crossref","is-referenced-by-count":0,"title":["A hybrid graph neural network for realized volatility forecasting: Multi-relation attention and dual-path fusion"],"prefix":"10.2139","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4077-0574","authenticated-orcid":true,"given":"Jongu","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5164-973X","authenticated-orcid":true,"given":"Woojin","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1019-4483","authenticated-orcid":true,"given":"Jungyoon","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"ref1","first-page":"701","volume":"89","author":"T G Andersen","year":"2007","journal-title":"Roughing it up: Including jump components in the measurement, modeling, and forecasting of return volatility. The review of economics and statistics"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1111\/1468-0262.00418","article-title":"Modeling and forecasting realized volatility","volume":"71","author":"T G Andersen","year":"2003","journal-title":"Econometrica"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1093\/rapstu\/raaa008","article-title":"The unprecedented stock market reaction to COVID-19","volume":"10","author":"S R Baker","year":"2020","journal-title":"The review of asset pricing studies"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1111\/1467-9868.00336","article-title":"Econometric analysis of realized volatility and its use in estimating stochastic volatility models","volume":"64","author":"O E Barndorff-Nielsen","year":"2002","journal-title":"Journal of the Royal Statistical Society Series B: Statistical Methodology"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/jjfinec\/nbh001","article-title":"Power and bipower variation with stochastic volatility and jumps","volume":"2","author":"O E Barndorff-Nielsen","year":"2004","journal-title":"Journal of financial econometrics"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/0304-4076(86)90063-1","article-title":"Generalized autoregressive conditional heteroskedasticity","volume":"31","author":"T Bollerslev","year":"1986","journal-title":"Journal of econometrics"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1093","DOI":"10.1016\/j.ijforecast.2024.11.004","article-title":"SpotV2Net: Multivariate intraday spot volatility forecasting via vol-of-vol-informed graph attention networks","volume":"41","author":"A Brini","year":"2025","journal-title":"International Journal of Forecasting"},{"key":"ref8","article-title":"How attentive are graph attention networks?","author":"S Brody","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1093\/jjfinec\/nbaa008","article-title":"Realized volatility forecasting with neural networks","volume":"18","author":"A Bucci","year":"2020","journal-title":"Journal of Financial Econometrics"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"6989","DOI":"10.1609\/aaai.v37i6.25854","article-title":"NHITS: Neural hierarchical interpolation for time series forecasting","author":"C Challu","year":"2023","journal-title":"Proceedings of the AAAI conference on artificial intelligence"},{"key":"ref11","first-page":"156","article-title":"Multivariate realized volatility forecasting with graph neural network","author":"Q Chen","year":"2022","journal-title":"Proceedings of the third acm international conference on ai in finance"},{"key":"ref12","first-page":"1655","article-title":"Incorporating corporation relationship via graph convolutional neural networks for stock price prediction","author":"Y Chen","year":"2018","journal-title":"Proceedings of the 27th ACM international conference on information and knowledge management"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1017\/S0022109014000428","article-title":"The economic value of realized volatility: Using high-frequency returns for option valuation","volume":"49","author":"P Christoffersen","year":"2014","journal-title":"Journal of Financial and Quantitative Analysis"},{"key":"ref14","article-title":"Economic links and predictable returns","volume":"63","author":"L Cohen","year":"1977","journal-title":"The Journal of Finance"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1093\/jjfinec\/nbp001","article-title":"A simple approximate long-memory model of realized volatility","volume":"7","author":"F Corsi","year":"2009","journal-title":"Journal of financial econometrics"},{"key":"ref16","first-page":"427","article-title":"Distribution of the estimators for autoregressive time series with a unit root","volume":"74","author":"D A Dickey","year":"1979","journal-title":"Journal of the American statistical association"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1198\/073500102753410444","article-title":"Comparing predictive accuracy","volume":"20","author":"F X Diebold","year":"2002","journal-title":"Journal of Business & economic statistics"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.jeconom.2014.04.012","article-title":"On the network topology of variance decompositions: Measuring the connectedness of financial firms","volume":"182","author":"F X Diebold","year":"2014","journal-title":"Journal of econometrics"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/B978-075066942-9.50004-2","article-title":"What good is a volatility model?","author":"R F Engle","year":"2007","journal-title":"Forecasting volatility in the financial markets"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1016\/j.ejor.2017.11.054","article-title":"Deep learning with long short-term memory networks for financial market predictions","volume":"270","author":"T Fischer","year":"2018","journal-title":"European journal of operational research"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1111\/0022-1082.00327","article-title":"The economic value of volatility timing","volume":"56","author":"J Fleming","year":"2001","journal-title":"The Journal of Finance"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1016\/S0304-405X(02)00259-3","article-title":"The economic value of volatility timing using \"realized\" volatility","volume":"67","author":"J Fleming","year":"2003","journal-title":"Journal of Financial Economics"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1779","DOI":"10.1111\/j.1540-6261.1993.tb05128.x","article-title":"On the relation between the expected value and the volatility of the nominal excess return on stocks","volume":"48","author":"L R Glosten","year":"1993","journal-title":"The journal of finance"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"453","DOI":"10.3982\/ECTA5771","article-title":"The model confidence set","volume":"79","author":"P R Hansen","year":"2011","journal-title":"Econometrica"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural computation"},{"key":"ref26","article-title":"A hybrid deep learning approach by integrating LSTM-ANN networks with GARCH model for copper price volatility prediction","volume":"557","author":"Y Hu","year":"2020","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1016\/j.jinteco.2023.103811","article-title":"Trade networks and firm value: Evidence from the US-China trade war","volume":"145","author":"Y Huang","year":"2023","journal-title":"Journal of International Economics"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.eswa.2018.03.002","article-title":"Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models","volume":"103","author":"H Y Kim","year":"2018","journal-title":"Expert Systems with Applications"},{"key":"ref29","article-title":"Semi-supervised classification with graph convolutional networks","author":"T N Kipf","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref30","article-title":"HGAIT: Heterogeneous graph attention with inverted transformers for correlation-aware stock return prediction","author":"D Lee","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"ref31","article-title":"Forecasting the realized volatility of stock price index: A hybrid model integrating CEEMDAN and LSTM","volume":"206","author":"Y Lin","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1002\/for.2897","article-title":"Trading volume and realized volatility forecasting: Evidence from the china stock market","volume":"42","author":"M Liu","year":"2023","journal-title":"Journal of Forecasting"},{"key":"ref33","first-page":"11116","article-title":"iTransformer: Inverted transformers are effective for time series forecasting","author":"Y Liu","year":"2024","journal-title":"International conference on learning representations"},{"key":"ref34","article-title":"Leveraging BiLSTM-GAT for enhanced stock market prediction: a dual-graph approach to portfolio optimization","volume":"55","author":"X Lu","year":"2025","journal-title":"Applied Intelligence"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108223","article-title":"Volatility forecasting and assessing risk of financial markets using Multi-Transformer neural network based architecture","volume":"133","author":"A K Mishra","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"1611","DOI":"10.1111\/jofi.12513","article-title":"Volatility-managed portfolios","volume":"72","author":"A Moreira","year":"2017","journal-title":"The Journal of Finance"},{"key":"ref37","article-title":"A time series is worth 64 words: Long-term forecasting with transformers","author":"Y Nie","year":"2023","journal-title":"The Eleventh International Conference on Learning Representations"},{"key":"ref38","article-title":"NeuralForecast: User friendly state-of-the-art neural forecasting models","author":"K G Olivares","year":"2022","journal-title":"PyCon Salt Lake City"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"884","DOI":"10.1016\/j.ijforecast.2022.03.001","article-title":"Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx","volume":"39","author":"K G Olivares","year":"2023","journal-title":"International Journal of Forecasting"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1016\/j.jeconom.2010.03.034","article-title":"Volatility forecast comparison using imperfect volatility proxies","volume":"160","author":"A J Patton","year":"2011","journal-title":"Journal of econometrics"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1257\/.41.2.478","article-title":"Forecasting volatility in financial markets: A review","volume":"41","author":"S H Poon","year":"2003","journal-title":"Journal of economic literature"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"M Schuster","year":"1997","journal-title":"IEEE transactions on Signal Processing"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"1539","DOI":"10.1002\/for.2975","article-title":"Forecasting global stock market volatility: The impact of volatility spillover index in spatial-temporal graph-based model","volume":"42","author":"B Son","year":"2023","journal-title":"Journal of Forecasting"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.113016","article-title":"Forecasting realized volatility using deep learning quantile function","volume":"175","author":"J Song","year":"2025","journal-title":"Applied Soft Computing"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1016\/j.jempfin.2010.04.008","article-title":"A network perspective of the stock market","volume":"17","author":"C K Tse","year":"2010","journal-title":"Journal of Empirical Finance"},{"key":"ref46","author":"A Vaswani","year":"2017","journal-title":"Attention is all you need. Advances in neural information processing systems 30"},{"key":"ref47","author":"P Veli\u010dkovi\u0107","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref48","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.113481","article-title":"Gold volatility prediction using a CNN-LSTM approach","volume":"157","author":"A Vidal","year":"2020","journal-title":"Expert Systems with Applications"},{"key":"ref49","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118128","article-title":"Stock market index prediction using deep transformer model","volume":"208","author":"C Wang","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"2022","DOI":"10.1145\/3308558.3313562","article-title":"Heterogeneous graph attention network","author":"X Wang","year":"2019","journal-title":"The world wide web conference"},{"key":"ref51","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1016\/j.ijforecast.2014.10.007","article-title":"Volatility forecasting: The role of lunch-break returns, overnight returns, trading volume and leverage effects","volume":"31","author":"X Wang","year":"2015","journal-title":"International Journal of Forecasting"},{"key":"ref52","first-page":"3584","article-title":"Temporal and heterogeneous graph neural network for financial time series prediction","author":"S Xiang","year":"2022","journal-title":"Proceedings of the 31st ACM international conference on information & knowledge management"},{"key":"ref53","doi-asserted-by":"crossref","DOI":"10.1007\/s11063-024-11479-2","article-title":"Gated fusion adaptive graph neural network for urban road traffic flow prediction","volume":"56","author":"L Xiong","year":"2024","journal-title":"Neural Processing Letters"},{"key":"ref54","first-page":"3634","article-title":"Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting","author":"B Yu","year":"2018","journal-title":"Proceedings of the 27th International Joint Conference on Artificial Intelligence"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"11121","DOI":"10.1609\/aaai.v37i9.26317","article-title":"Are transformers effective for time series forecasting?","author":"A Zeng","year":"2023","journal-title":"Proceedings of the AAAI conference on artificial intelligence"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1016\/j.ijforecast.2024.09.002","article-title":"Forecasting realized volatility with spillover effects: Perspectives from graph neural networks","volume":"41","author":"C Zhang","year":"2025","journal-title":"International Journal of Forecasting"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"16998","DOI":"10.1609\/aaai.v38i15.29643","article-title":"From GARCH to neural network for volatility forecast","author":"P Zhao","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"}],"container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T12:50:41Z","timestamp":1791377441000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=7576359"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":57,"URL":"https:\/\/doi.org\/10.2139\/ssrn.7576359","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}