{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T05:08:02Z","timestamp":1789103282556,"version":"build-2803163510"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Exchange-rate return forecasting is challenging because financial time series may exhibit linearity, nonlinearity, regime-switching behavior, and volatility. To address these complexities, two adaptive hybrid forecasting frameworks were developed: ATW-HyF A, which dynamically combines ARIMA, SETAR, and ANN forecasts using inverse-variance weighting, and ATW-HyF B, which extends the framework by incorporating a GARCH(1,1) volatility layer to model the conditional variance of forecast errors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The robustness of the proposed frameworks was assessed using simulated data and three foreign exchange return series: USD\/NGN, EUR\/USD, and GBP\/USD. Forecast performance was evaluated within a rolling-origin forecasting framework and compared with competing forecasting models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The simulation results showed that the ATW-HyF models achieved the lowest forecast errors among the competing models. However, their performance on the empirical exchange-rate series was mixed, with other models achieving lower forecast errors for some currency pairs. In particular, the ARIMA-ANN hybrid performed best for USD\/NGN and EUR\/USD, whereas ATW-HyF B performed best for GBP\/USD.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The findings indicate that forecasting performance depends on the characteristics of the underlying exchange-rate series rather than on model complexity alone. Combining models with complementary predictive strengths can improve forecasting performance, particularly when the data exhibit linear, nonlinear, and volatility-related patterns. The incorporation of adaptive weighting and volatility modeling therefore provides a flexible approach to exchange-rate return forecasting under evolving market conditions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fdata.2026.1917723","type":"journal-article","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T04:34:45Z","timestamp":1789101285000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Data-driven adaptive hybrid models for exchange rate return forecasting"],"prefix":"10.3389","volume":"9","author":[{"given":"Olumide Sunday","family":"Adesina","sequence":"first","affiliation":[{"name":"Johannesburg Business School, University of Johannesburg","place":["Johannesburg, South Africa"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lawrence Ogechukwu","family":"Obokoh","sequence":"additional","affiliation":[{"name":"Johannesburg Business School, University of Johannesburg","place":["Johannesburg, South Africa"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1447","DOI":"10.18280\/ijsse.140512","article-title":"Bayesian modelling of tail risk using extreme value theory with application to currency exchange","volume":"14","author":"Adesina","year":"2024","journal-title":"Int. J. Saf. Secur. Eng."},{"key":"B2","doi-asserted-by":"publisher","first-page":"e02818","DOI":"10.1016\/j.sciaf.2025.e02818","article-title":"A hybrid framework of deep learning and traditional time series models for exchange rate prediction","volume":"29","author":"Adesina","year":"2025","journal-title":"Scient. African"},{"key":"B3","unstructured":"\u201cPredicting the South African stock market using the hybrid of LSTM-ARFIMA model,\u201d\n          \n          \n            \n              Adesina\n              O. S.\n            \n            \n              Obokoh\n              L. O.\n            \n          \n          Springer Proceedings in Business and Economics\n          \n          2026"},{"key":"B4","doi-asserted-by":"publisher","first-page":"102067","DOI":"10.1016\/j.intfin.2024.102067","article-title":"Forecasting exchange rate volatility: An amalgamation approach","volume":"97","author":"Alexandridis","year":"2024","journal-title":"J. Int. Finan. Markets Institut. Money"},{"key":"B5","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1057\/jors.1969.103","article-title":"The combination of forecasts","volume":"20","author":"Bates","year":"1969","journal-title":"Oper. Res. Q."},{"key":"B6","first-page":"702","article-title":"Exchange rate predictability and economic policy uncertainty","volume":"101","author":"Beckmann","year":"2017","journal-title":"Eur. Econ. Rev."},{"key":"B7","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/0304-4076(86)90063-1","article-title":"Generalized autoregressive conditional heteroskedasticity","volume":"31","author":"Bollerslev","year":"1986","journal-title":"J. Econom."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jimonfin.2015.12.001","article-title":"Exchange rate predictability in a changing world","volume":"64","author":"Byrne","year":"2016","journal-title":"J. Int. Money Finan."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1016\/j.jimonfin.2005.08.002","article-title":"Empirical exchange rate models of the nineties: are any fit to survive?","volume":"24","author":"Cheung","year":"2005","journal-title":"J. Int. Money Finan."},{"key":"B10","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1080\/07350015.1995.10524599","article-title":"Comparing predictive accuracy","volume":"13","author":"Diebold","year":"1995","journal-title":"J. Busi. Econ. Statist."},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1109\/ICOA66896.2025.11236930","article-title":"\u201cCombining ARDL and tree-based machine learning methods to assess the impact of exchange rate volatility on Moroccan foreign trade,\u201d","volume-title":"2025 11th International Conference on Optimization and Applications (ICOA)","author":"El Kadri","year":"2025"},{"key":"B12","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1086\/429137","article-title":"Exchange rates and fundamentals","volume":"113","author":"Engel","year":"2005","journal-title":"J. Polit. Econ."},{"key":"B13","doi-asserted-by":"publisher","first-page":"987","DOI":"10.2307\/1912773","article-title":"Autoregressive conditional heteroskedasticity with estimates of UK inflation","volume":"50","author":"Engle","year":"1982","journal-title":"Econometrica"},{"key":"B14","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1257\/000282805774669934","article-title":"Meese\u2013Rogoff redux: micro-based exchange-rate forecasting","volume":"95","author":"Evans","year":"2005","journal-title":"Am. Econ. Rev."},{"key":"B15","doi-asserted-by":"publisher","first-page":"125590","DOI":"10.1016\/j.eswa.2024.125590","article-title":"Multi-scale contrast approach for stock index prediction with adaptive stock fusion","volume":"262","author":"Gao","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"B16","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"B17","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/S0169-2070(96)00719-4","article-title":"Testing the equality of prediction mean squared errors","volume":"13","author":"Harvey","year":"1997","journal-title":"Int. J. Forecast."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.najef.2024.102148","article-title":"Forecasting conditional volatility based on hybrid GARCH-type models with long memory, regime switching, leverage effect and heavy-tail: Further evidence from equity market","author":"Huang","year":"2024","journal-title":"North Am. J. Econ. Finan."},{"key":"B19","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib: A 2D graphics environment","volume":"9","author":"Hunter","year":"2007","journal-title":"Comp. Sci. Eng."},{"key":"B20","doi-asserted-by":"publisher","first-page":"127696","DOI":"10.1016\/j.eswa.2025.127696","article-title":"Effect of exogenous market sentiment indicators in stock price direction prediction","volume":"281","author":"Keun Yun","year":"2025","journal-title":"Expert Systems Appl."},{"key":"B21","doi-asserted-by":"publisher","first-page":"2664","DOI":"10.1016\/j.asoc.2010.10.015","article-title":"A novel hybridization of artificial neural networks and ARIMA models","volume":"11","author":"Khashei","year":"2011","journal-title":"Appl. Soft Comput."},{"key":"B22","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.iref.2020.05.001","article-title":"Exchange rate predictability: a variable selection perspective","volume":"70","author":"Kim","year":"2020","journal-title":"Int. Rev. Econ. Finan."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.eswa.2018.05.01","article-title":"A hybrid volatility forecasting framework integrating GARCH, artificial neural network, technical analysis and principal components analysis","volume":"109","author":"Kristjanpoller","year":"2018","journal-title":"Expert Systems Appli"},{"key":"B24","doi-asserted-by":"publisher","first-page":"123948","DOI":"10.1016\/j.eswa.2024.123948","article-title":"Enhanced stock price forecasting through a regularized ensemble framework with graph convolutional networks","volume":"250","author":"Ma","year":"2024","journal-title":"Expert Systems Appli"},{"key":"B25","doi-asserted-by":"publisher","first-page":"e0194889","DOI":"10.1371\/journal.pone.0194889","article-title":"Statistical and machine learning forecasting methods: concerns and ways forward","volume":"13","author":"Makridakis","year":"2018","journal-title":"PLOS ONE"},{"key":"B26","doi-asserted-by":"publisher","first-page":"51","DOI":"10.25080\/Majora-92bf1922-00a","article-title":"\u201cData structures for statistical computing in Python,\u201d","author":"McKinney","year":"2010","journal-title":"Proceedings of the 9th Python in Science Conference"},{"key":"B27","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/0022-1996(83)90017-X","article-title":"Empirical exchange rate models of the seventies: do they fit out of sample?","volume":"14","author":"Meese","year":"1983","journal-title":"J. Int. Econ."},{"key":"B28","doi-asserted-by":"publisher","first-page":"3340","DOI":"10.1080\/00036846.2012.709605","article-title":"Why is it so difficult to outperform the random walk?","volume":"45","author":"Moosa","year":"2013","journal-title":"Appl. Econ."},{"key":"B29","doi-asserted-by":"publisher","first-page":"129068","DOI":"10.1016\/j.eswa.2025.129068","article-title":"A hybrid fuzzy-CNN model with feature extraction from MACD-based trends for stock market movement forecasting","volume":"296","author":"\u00d6zdo\u011fan","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"B30","unstructured":"Scikit-learn: machine learning in Python\n          \n          2825\n          2830\n          \n            \n              Pedregosa\n              F.\n            \n            \n              Varoquaux\n              G.\n            \n            \n              Gramfort\n              A.\n            \n            \n              Michel\n              V.\n            \n            \n              Thirion\n              B.\n            \n            \n              Grisel\n              O.\n            \n          \n          J. Machine Learn. Res.\n          12\n          2011"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1257\/jel.51.4.1063","article-title":"Exchange rate predictability","volume":"51","author":"Rossi","year":"2013","journal-title":"J. Econ. Lit."},{"key":"B32","doi-asserted-by":"crossref","unstructured":"\u201cStatsmodels: econometric and statistical modeling with Python,\u201d\n          \n          92\n          96\n          \n            \n              Seabold\n              S.\n            \n            \n              Perktold\n              J.\n            \n          \n          Austin, TX\n          SciPy\n          Proceedings of the 9th Python in Science Conference\n          \n          2010","DOI":"10.25080\/Majora-92bf1922-011"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10981635","article-title":"bashtage\/arch: Release 7.0.0 (Version v7.0.0) [Computer software]","author":"Sheppard","year":"2024","journal-title":"Zenodo"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.sciaf.2026.e03345","article-title":"Predictive modelling of hydrogen adsorption energy using hybrid EMT and machine learning techniques","volume":"32","author":"Solomon","year":"2026","journal-title":"Scientif. African"},{"key":"B35","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1002\/for.928","article-title":"Combination forecasts of output growth in a seven-country dataset","volume":"23","author":"Stock","year":"2004","journal-title":"J. Forecast."},{"key":"B36","doi-asserted-by":"publisher","first-page":"121899","DOI":"10.1016\/j.eswa.2023.121899","article-title":"Attention based adaptive spatial\u2013temporal hypergraph convolutional networks for stock price trend prediction","volume":"238","author":"Su","year":"2024","journal-title":"Expert Syst. Appli."},{"key":"B37","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/S1574-0706(05)01004-9","article-title":"Forecast combinations","volume":"1","author":"Timmermann","year":"2006","journal-title":"Handbook Econ. Forecast."},{"key":"B38","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1518","DOI":"10.1016\/j.ijforecast.2022.11.005","article-title":"Forecast combinations: an over 50-year review","volume":"39","author":"Wang","year":"2022","journal-title":"Int. J. Forecast."},{"key":"B40","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/S0925-2312(01)00702-0","article-title":"Time series forecasting using a hybrid ARIMA and neural network model","volume":"50","author":"Zhang","year":"2003","journal-title":"Neurocomputing"},{"key":"B41","doi-asserted-by":"publisher","first-page":"117239","DOI":"10.1016\/j.eswa.2022.117239","article-title":"Transformer-based at tention network for stock movement prediction","volume":"202","author":"Zhang","year":"2022","journal-title":"Expert Syst. Appl."}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2026.1917723\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T04:34:49Z","timestamp":1789101289000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2026.1917723\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,11]]},"references-count":41,"alternative-id":["10.3389\/fdata.2026.1917723"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2026.1917723","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,11]]},"article-number":"1917723"}}