{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T14:50:18Z","timestamp":1791816618100,"version":"4.3.4"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":41,"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>Gasoline price volatility poses substantial risks for refiners, distributors, hedgers, and policymakers, yet models that perform well in point prediction need not provide equally reliable measures of conditional risk. This study uses an entropy-regularized hypergraph neural network (ERHNN) to forecast the conditional distribution of U.S. gasoline returns using weekly data from 2000 to 2025. The model combines a fixed relational representation linking crude-oil returns, crack spreads, inventories, refinery utilization, and financial conditions; a conditional Student-t predictive density; and entropy-motivated scale regularization designed to stabilize time-varying volatility. The ERHNN is evaluated against conventional volatility models, recurrent neural networks, and tree-based machine-learning benchmarks using RMSE, QLIKE, CRPS, prediction-interval coverage, and Value-at-Risk backtests. Random Forest and XGBoost achieve slightly lower RMSE, but ERHNN records the lowest CRPS and QLIKE, attains 94.7% coverage for the nominal 95% prediction interval. Neither the Kupiec nor the Dynamic Quantile tests reject the corresponding VaR calibration null for ERHNN. ERHNN records the lowest QLIKE in both high- and low-volatility states. Ablation results further show that removing the hypergraph, replacing the Student-t density with a Gaussian specification, or removing entropy regularization substantially worsens QLIKE, although restricted specifications can outperform the full model on individual point or VaR-frequency criteria. The findings therefore establish a clear distinction between point predictability and risk predictability: the model that best forecasts realized gasoline returns need not be the model that best characterizes the uncertainty surrounding those returns.<\/jats:p>","DOI":"10.2139\/ssrn.7601728","type":"posted-content","created":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T14:38:41Z","timestamp":1791815921000},"source":"Crossref","is-referenced-by-count":0,"title":["Economic Rational Structure and Distributional Risk Forecasting in Gasoline Market"],"prefix":"10.2139","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5171-1634","authenticated-orcid":true,"given":"Bismark","family":"Asante","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1487-2438","authenticated-orcid":true,"given":"William","family":"Nganje","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel  Anu","family":"Thompson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Ripplinger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"5","key":"ref1","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1162\/REST_a_00419","article-title":"Gasoline prices, fuel economy, and the energy paradox","volume":"96","author":"H Allcott","year":"2014","journal-title":"Review of Economics and Statistics"},{"issue":"3","key":"ref2","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1016\/j.jeem.2013.07.002","article-title":"What do consumers believe about future gasoline prices","volume":"66","author":"S T Anderson","year":"2013","journal-title":"Journal of Environmental Economics and Management"},{"issue":"3","key":"ref3","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1162\/003465303322369902","article-title":"New evidence on asymmetric gasoline price responses","volume":"85","author":"L J Bachmeier","year":"2003","journal-title":"Review of Economics and Statistics"},{"issue":"S1","key":"ref4","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.eneco.2014.08.006","article-title":"Forecasting the oil-gasoline price relationship: Do asymmetries help?","volume":"46","author":"A Bastianin","year":"2014","journal-title":"Energy Economics"},{"key":"ref5","article-title":"Forecasting crude oil volatility with exogenous predictors: As good as it GETS?","volume":"111","author":"J.-B Bonnier","year":"2022","journal-title":"Energy Economics"},{"issue":"1","key":"ref6","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1162\/003355397555118","article-title":"Do gasoline prices respond asymmetrically to crude oil price changes?","volume":"112","author":"S Borenstein","year":"1997","journal-title":"Quarterly Journal of Economics"},{"issue":"3","key":"ref7","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1017\/S1365100516000249","article-title":"Oil, uncertainty, and gasoline prices","volume":"22","author":"D Chang","year":"2018","journal-title":"Macroeconomic Dynamics"},{"issue":"3","key":"ref8","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1080\/07350015.1995.10524599","article-title":"Comparing predictive accuracy","volume":"13","author":"F X Diebold","year":"2002","journal-title":"Journal of Business & Economic Statistics"},{"issue":"1","key":"ref9","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.ijforecast.2011.02.006","article-title":"Better to give than to receive: Predictive directional measurement of volatility spillovers","volume":"28","author":"F X Diebold","year":"2012","journal-title":"International Journal of Forecasting"},{"issue":"3","key":"ref10","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1162\/REST_a_00300","article-title":"Stock market volatility and macroeconomic fundamentals","volume":"95","author":"R F Engle","year":"2013","journal-title":"Review of Economics and Statistics"},{"issue":"4","key":"ref11","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1198\/073500104000000370","article-title":"CAViaR: Conditional autoregressive Value at Risk by regression quantiles","volume":"22","author":"R F Engle","year":"2004","journal-title":"Journal of Business & Economic Statistics"},{"issue":"2","key":"ref12","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1111\/j.1467-9868.2007.00587.x","article-title":"Probabilistic forecasts, calibration and sharpness","volume":"69","author":"T Gneiting","year":"2007","journal-title":"Journal of the Royal Statistical Society Series B: Statistical Methodology"},{"issue":"477","key":"ref13","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1198\/016214506000001437","article-title":"Strictly proper scoring rules, prediction, and estimation","volume":"102","author":"T Gneiting","year":"2007","journal-title":"Journal of the American Statistical Association"},{"issue":"8","key":"ref14","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"},{"issue":"4","key":"ref15","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1103\/PhysRev.106.620","article-title":"Information theory and statistical mechanics","volume":"106","author":"E T Jaynes","year":"1957","journal-title":"Physical Review"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.eneco.2018.08.013","article-title":"Information spillovers and connectedness networks in the oil and gas markets","volume":"75","author":"Q Ji","year":"2018","journal-title":"Energy Economics"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.eneco.2012.09.010","article-title":"Modeling and forecasting the volatility of petroleum futures prices","volume":"36","author":"S H Kang","year":"2013","journal-title":"Energy Economics"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1016\/j.eneco.2014.06.004","article-title":"Macro determinants of volatility and volatility spillover in energy markets","volume":"46","author":"B Karali","year":"2014","journal-title":"Energy Economics"},{"issue":"2","key":"ref19","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1016\/j.enpol.2008.09.052","article-title":"Horizontal and vertical transmissions in the US oil supply chain","volume":"37","author":"R K Kaufmann","year":"2009","journal-title":"Energy Policy"},{"issue":"2","key":"ref20","doi-asserted-by":"crossref","first-page":"87","DOI":"10.5547\/ISSN0195-6574-EJ-Vol31-No2-4","article-title":"Explaining fluctuations in gasoline prices: A joint model of the global crude oil market and the U.S. retail gasoline market","volume":"31","author":"L Kilian","year":"2010","journal-title":"Energy Journal"},{"issue":"1","key":"ref21","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.eneco.2011.08.008","article-title":"Inventories and upstream gasoline price dynamics","volume":"34","author":"G H Kuper","year":"2012","journal-title":"Energy Economics"},{"issue":"2","key":"ref22","doi-asserted-by":"crossref","first-page":"73","DOI":"10.3905\/jod.1995.407942","article-title":"Techniques for verifying the accuracy of risk measurement models","volume":"3","author":"P H Kupiec","year":"1995","journal-title":"Journal of Derivatives"},{"key":"ref23","article-title":"Forecasting crude oil volatility with uncertainty indicators: New evidence","volume":"108","author":"X Li","year":"2022","journal-title":"Energy Economics"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.eneco.2013.03.001","article-title":"Gasoline price volatility and the elasticity of demand for gasoline","volume":"38","author":"C.-Y C Lin","year":"2013","journal-title":"Energy Economics"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.eneco.2018.08.010","article-title":"Predictability of crude oil prices: An investor perspective","volume":"75","author":"L Liu","year":"2018","journal-title":"Energy Economics"},{"key":"ref26","article-title":"A unified approach to interpreting model predictions","author":"S M Lundberg","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","article-title":"Changing determinant driver and oil volatility forecasting: A comprehensive analysis","volume":"129","author":"Q Luo","year":"2024","journal-title":"Energy Economics"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.eneco.2017.08.004","article-title":"Forecasting the realized volatility of the oil futures market: A regime switching approach","volume":"67","author":"F Ma","year":"2017","journal-title":"Energy Economics"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1016\/j.eneco.2020.104757","article-title":"Forecasting crude oil and refined products volatilities and correlations: New evidence from fractionally integrated multivariate GARCH models","volume":"88","author":"M Marchese","year":"2020","journal-title":"Energy Economics"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1016\/j.eneco.2023.106843","article-title":"Distributional neural networks for electricity price forecasting","volume":"125","author":"G Marcjasz","year":"2023","journal-title":"Energy Economics"},{"key":"ref31","article-title":"The role of uncertainty measures in volatility forecasting of the crude oil futures market before and during the COVID-19 pandemic","volume":"112","author":"Z Niu","year":"2022","journal-title":"Energy Economics"},{"key":"ref32","first-page":"321","volume":"33","author":"N K Nomikos","year":"2011","journal-title":"Forecasting petroleum futures markets volatility: The role of regimes and market conditions"},{"issue":"1","key":"ref33","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"},{"issue":"8","key":"ref34","doi-asserted-by":"crossref","first-page":"758","DOI":"10.1002\/fut.21759","article-title":"Do jumps matter for volatility forecasting? Evidence from energy markets","volume":"36","author":"M Prokopczuk","year":"2016","journal-title":"Journal of Futures Markets"},{"issue":"4","key":"ref35","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1016\/j.eneco.2005.04.004","article-title":"Lags in the response of gasoline prices to changes in crude oil prices: The role of short-term and long-term shocks","volume":"27","author":"S Radchenko","year":"2005","journal-title":"Energy Economics"},{"issue":"4","key":"ref36","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1016\/j.eneco.2006.04.005","article-title":"Modeling and forecasting petroleum futures volatility","volume":"28","author":"P Sadorsky","year":"2006","journal-title":"Energy Economics"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1016\/j.eneco.2024.107608","article-title":"Unraveling the crystal ball: Machine learning models for crude oil and natural gas volatility forecasting","volume":"134","author":"A K Tiwari","year":"2024","journal-title":"Energy Economics"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.eneco.2016.05.004","article-title":"What the investors need to know about forecasting oil futures return volatility","volume":"57","author":"Y Wang","year":"2016","journal-title":"Energy Economics"},{"issue":"3","key":"ref39","doi-asserted-by":"crossref","first-page":"1022","DOI":"10.1016\/j.ijforecast.2023.09.002","article-title":"Forecasting crude oil market volatility: A comprehensive look at uncertainty variables","volume":"40","author":"D Wen","year":"2024","journal-title":"International Journal of Forecasting"},{"issue":"1","key":"ref40","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":"ref41","article-title":"AI-driven hypergraph neural network for predicting gasoline price trends","volume":"151","author":"P Zhu","year":"2025","journal-title":"Energy Economics"}],"container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T14:42:06Z","timestamp":1791816126000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=7601728"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":41,"URL":"https:\/\/doi.org\/10.2139\/ssrn.7601728","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}