{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:52:10Z","timestamp":1784389930116,"version":"3.55.0"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,2,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The international currency exchange market, known for its speculative and volatile nature, operates within a complex financial ecosystem. Compared to other investment domains, it exhibits lower efficiency, highlighting the need for advanced predictive frameworks. This study introduces TFT-ICENet, a temporal fusion transformer network enhanced with temporal attention mechanisms, designed to improve accuracy in forecasting exchange rates. TFT-ICENet uses temporal attention mechanisms to extract data from various historical intervals and integrates long-term and short-term features through TFTs, significantly enhancing multi-step prediction precision. Extensive experiments were conducted using four comprehensive datasets capturing the volatility of major currencies, including the US dollar, euro, renminbi, yen, and Australian dollar. The model was compared against state-of-the-art algorithms to evaluate its generalizability and robustness. Results show TFT-ICENet\u2019s superior predictive performance, with reduced mean squared error and high $R^{2}$ scores, reflecting its accuracy. It also outperforms baseline models in mean absolute error, confirming its reliability. TFT-ICENet not only surpasses existing methodologies but also sets a new standard for analyzing the currency exchange market, offering investors a powerful tool for decision-making and strategic planning.<\/jats:p>","DOI":"10.1093\/comjnl\/bxaf113","type":"journal-article","created":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T11:30:56Z","timestamp":1757244656000},"page":"259-271","source":"Crossref","is-referenced-by-count":1,"title":["A temporal fusion transformer network for enhanced international currency exchange prediction"],"prefix":"10.1093","volume":"69","author":[{"given":"Dixuan","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Artificial Intelligence , Zhengzhou University, Zhengzhou, Henan 450000,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"2026021823461649300_ref1","doi-asserted-by":"crossref","DOI":"10.1109\/MECON67253.2025.11276931","article-title":"Advancing exchange rate forecasting: leveraging machine learning and AI for enhanced accuracy in global financial markets","author":"Rahat","year":"2025"},{"key":"2026021823461649300_ref2","doi-asserted-by":"crossref","DOI":"10.5089\/9781589063587.084","volume-title":"A New Look at Exchange Rate Volatility and Trade Flows","author":"Clark","year":"2004"},{"key":"2026021823461649300_ref3","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1136\/bmj.303.6817.1565","article-title":"Chaos\u2013predicting the unpredictable","volume":"303","author":"Firth","year":"1991","journal-title":"BMJ"},{"key":"2026021823461649300_ref4","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1108\/GS-12-2019-0068","article-title":"Forecasting the price trends of digital currency: a hybrid model integrating the stochastic index and grey markov chain methods","volume":"11","author":"Shou","year":"2020","journal-title":"Grey Syst Theory and Appl"},{"key":"2026021823461649300_ref5","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/j.ins.2019.01.076","article-title":"Evaluation of statistical and machine learning models for time series prediction: identifying the state-of-the-art and the best conditions for the use of each model","volume":"484","author":"Parmezan","year":"2019","journal-title":"Inform Sci"},{"key":"2026021823461649300_ref6","doi-asserted-by":"crossref","first-page":"20200209","DOI":"10.1098\/rsta.2020.0209","article-title":"Time-series forecasting with deep learning: a survey","volume":"379","author":"Lim","year":"2021","journal-title":"Philos Trans R Soc A"},{"key":"2026021823461649300_ref7","first-page":"229","article-title":"Autoregressive tree models for time-series analysis","volume-title":"Proceedings of the 2nd SIAM International Conference on Data Mining (SDM)","author":"Meek","year":"2002"},{"key":"2026021823461649300_ref8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/4758698","article-title":"Research on stock price time series prediction based on deep learning and autoregressive integrated moving average","volume":"2022","author":"Xiao","year":"2022","journal-title":"Sci Program"},{"key":"2026021823461649300_ref9","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1016\/0261-5606(91)90036-J","article-title":"Some linear and nonlinear thoughts on exchange rates","volume":"10","author":"Chinn","year":"1991","journal-title":"J Int Money Finance"},{"key":"2026021823461649300_ref10","first-page":"251","article-title":"Foreign currency exchange rate prediction using long short-term memory, support vector regression and random forest regression","volume-title":"Financial Data Analytics: Theory and Application","author":"Rabbi"},{"key":"2026021823461649300_ref11","first-page":"434","article-title":"Machine learning approaches for financial time series forecasting","volume-title":"Proceedings of the Selected Papers of the Special Edition of International Conference on Monitoring, Modeling & Management of Emergent Economy (M3E2-MLPEED)","author":"Derbentsev","year":"2020"},{"key":"2026021823461649300_ref12","doi-asserted-by":"publisher","DOI":"10.3390\/info11060332","article-title":"Evaluation of tree-based ensemble machine learning models in predicting stock price direction of movement","volume":"11","author":"Ampomah","year":"2020","journal-title":"Information"},{"key":"2026021823461649300_ref13","first-page":"755","article-title":"Fake currency detection with machine learning algorithm and image processing","volume-title":"Proceedings of the 5th International Conference on Intelligent Computing and Control Systems (ICICCS)","author":"Bhatia","year":"2021"},{"key":"2026021823461649300_ref14","article-title":"Currency exchange prediction using machine learning, genetic algorithms and technical analysis","author":"Abreu"},{"key":"2026021823461649300_ref15","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1016\/j.ijforecast.2020.06.008","article-title":"Recurrent neural networks for time series forecasting: Current status and future directions","volume":"37","author":"Hewamalage","year":"2021","journal-title":"Int J Forecasting"},{"key":"2026021823461649300_ref16","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1109\/MCOM.2019.1800155","article-title":"Deep learning with long short-term memory for time series prediction","volume":"57","author":"Hua","year":"2019","journal-title":"IEEE Commun Mag"},{"key":"2026021823461649300_ref17","doi-asserted-by":"publisher","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":"Fischer","year":"2018","journal-title":"Eur J Oper Res"},{"key":"2026021823461649300_ref18","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1016\/j.procs.2022.01.149","article-title":"Price change prediction of ultra high frequency financial data based on temporal convolutional network","volume":"199","author":"Dai","year":"2022","journal-title":"Procedia Comput Sci"},{"key":"2026021823461649300_ref19","doi-asserted-by":"crossref","first-page":"657","DOI":"10.3390\/e24050657","article-title":"Neural networks for financial time series forecasting","volume":"24","author":"Sako","year":"2022","journal-title":"Entropy"},{"key":"2026021823461649300_ref20","doi-asserted-by":"publisher","first-page":"17193","DOI":"10.1007\/s00521-022-07687-3","article-title":"Event prediction within directional change framework using a CNN-LSTM model","volume":"34","author":"Rostamian","year":"2022","journal-title":"Neural Comput Appl"},{"key":"2026021823461649300_ref21","doi-asserted-by":"publisher","first-page":"14153","DOI":"10.1007\/s11042-022-12328-x","article-title":"A stock market trading framework based on deep learning architectures","volume":"81","author":"Shah","year":"2022","journal-title":"Multimed Tools Appl"},{"key":"2026021823461649300_ref22","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13317","article-title":"Is attention all you need for intraday forex trading?","volume":"41","author":"Gradzki","year":"2024","journal-title":"Expert Syst"},{"key":"2026021823461649300_ref23","doi-asserted-by":"publisher","first-page":"153083","DOI":"10.1109\/ACCESS.2021.3127570","article-title":"Can deep learning improve technical analysis of forex data to predict future price movements?","volume":"9","author":"Fisichella","year":"2021","journal-title":"IEEE Access"},{"key":"2026021823461649300_ref24","first-page":"211","article-title":"Applications of artificial neural networks in financial economics: a survey","volume-title":"Proceedings of the 3rd International Symposium on Computational Intelligence and Design (ISCID)","author":"Li","year":"2010"},{"key":"2026021823461649300_ref25","doi-asserted-by":"crossref","first-page":"126302","DOI":"10.1016\/j.eswa.2024.126302","article-title":"Multivariate time series prediction with multi-feature analysis","volume":"268","author":"Chen","year":"2025","journal-title":"Expert Syst Appl"},{"key":"2026021823461649300_ref26","doi-asserted-by":"publisher","first-page":"2477","DOI":"10.1007\/s10614-023-10529-6","article-title":"Machine learning-based time series prediction at brazilian stocks exchange","volume":"64","author":"dos Santos Gularte","year":"2024","journal-title":"Comput Econ"},{"key":"2026021823461649300_ref27","doi-asserted-by":"publisher","first-page":"537","DOI":"10.3390\/math13030537","article-title":"Traditional prediction techniques and machine learning approaches for financial time series analysis","volume":"13","author":"Cappello","year":"2025","journal-title":"Mathematics"},{"key":"2026021823461649300_ref28","doi-asserted-by":"crossref","first-page":"5957","DOI":"10.3390\/app15115957","article-title":"A survey of machine learning methods for time series prediction","volume":"15","author":"Hall","year":"2025","journal-title":"Appl Sci"},{"key":"2026021823461649300_ref29","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1007\/s10614-023-10499-9","article-title":"Hybridization of ARIMA with learning models for forecasting of stock market time series","volume":"63","author":"Pokou","year":"2024","journal-title":"Comput Econ"},{"key":"2026021823461649300_ref30","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1016\/j.procs.2025.01.050","article-title":"Stock market time series forecasting using comparative machine learning algorithms","volume":"252","author":"Gupta","year":"2025","journal-title":"Procedia Comput Sci"},{"key":"2026021823461649300_ref31","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s42452-024-06409-9","article-title":"Correction: hybrid GNSS time-series prediction method based on ensemble empirical mode decomposition with long short-term memory","volume":"7","author":"Zhou","year":"2025","journal-title":"Discover Appl Sci"},{"key":"2026021823461649300_ref32","first-page":"2627","article-title":"A dual-stage attention-based recurrent neural network for time series prediction","volume-title":"Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI)","author":"Qin","year":"2017"},{"key":"2026021823461649300_ref33","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1162\/089976600300015015","article-title":"Learning to forget: continual prediction with LSTM","volume":"12","author":"Gers","year":"2000","journal-title":"Neural Comput"},{"key":"2026021823461649300_ref34","article-title":"Staudemeyer and Eric Rothstein Morris. Understanding LSTM\u2014a tutorial into long short-term memory recurrent neural networks","author":"Ralf","year":"2019"},{"key":"2026021823461649300_ref35","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A review of recurrent neural networks: LSTM cells and network architectures","volume":"31","author":"Yu","year":"2019","journal-title":"Neural Comput"},{"key":"2026021823461649300_ref36","article-title":"Supplementary technical report: model performance and ablation studies for multi-step exchange rate forecasting. GitHub; 2025.","author":"Zhang"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/advance-article-pdf\/doi\/10.1093\/comjnl\/bxaf113\/64418369\/bxaf113.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/advance-article-pdf\/doi\/10.1093\/comjnl\/bxaf113\/64418369\/bxaf113.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T04:46:29Z","timestamp":1771476389000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/69\/2\/259\/8266855"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":36,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,9,27]]},"published-print":{"date-parts":[[2026,2,15]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxaf113","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,2]]},"published":{"date-parts":[[2025,9,27]]}}}