{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:42:52Z","timestamp":1782574972000,"version":"3.54.5"},"reference-count":57,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"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. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Transformer models have demonstrated remarkable performance in financial time series forecasting. However, they suffer from inefficiencies in computational efficiency, high operational costs, and limitations in capturing temporal dependencies.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To address these challenges, we propose the CMDMamba model, which is based on the Mamba architecture of state-space models (SSMs) and achieves near-linear time complexity. This significantly enhances the real-time data processing capability and reduces the deployment costs for risk management systems. The CMDMamba model employs a dual-layer Mamba structure that effectively captures price fluctuations at both the micro- and macrolevels in financial markets and integrates an innovative Dual Convolutional Feedforward Network (DconvFFN) module. This module is able to effectively capture the correlations between multiple variables in financial markets. By doing so, it provides more accurate time series modeling, optimizes algorithmic trading strategies, and facilitates investment portfolio risk warnings.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Experiments conducted on four real-world financial datasets demonstrate that CMDMamba achieves a 10.4% improvement in prediction accuracy for multivariate forecasting tasks compared to state-of-the-art models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>Moreover, CMDMamba excels in both predictive accuracy and computational efficiency, setting a new benchmark in the field of financial time series forecasting.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2025.1599799","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T05:25:13Z","timestamp":1752557113000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["CMDMamba: dual-layer Mamba architecture with dual convolutional feed-forward networks for efficient financial time series forecasting"],"prefix":"10.3389","volume":"8","author":[{"given":"Zhenkai","family":"Qin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baozhong","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujia","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqian","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaochuan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingxuan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"B1","first-page":"1688","article-title":"\u201cTimemachine: a time series is worth 4 mambas for long-term forecasting,\u201d","author":"Ahamed","year":"2024","journal-title":"ECAI 2024 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain - Including 13th Conference on Prestigious Applications of Intelligent Systems European Conference on Artificial Intelligence"},{"key":"B2","doi-asserted-by":"publisher","first-page":"4401","DOI":"10.1007\/s11831-023-09942-9","article-title":"A comprehensive survey on higher order neural networks and evolutionary optimization learning algorithms in financial time series forecasting","volume":"30","author":"Behera","year":"2023","journal-title":"Arch. Comp. Methods Eng"},{"key":"B3","article-title":"Chimera: effectively modeling multivariate time series with 2dimensional state space models","author":"Behrouz","year":"","journal-title":"arXiv preprint"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.19888","article-title":"MambaMixer: efficient selective state space models with dual token and channel selection","author":"Behrouz","year":"","journal-title":"arXiv"},{"key":"B5","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1007\/s12197-020-09505-9","article-title":"Financial market risk and macroeconomic stability variables: dynamic interactions and feedback effects","volume":"44","author":"Chomicz-Grabowska","year":"2020","journal-title":"J. Econ. Finance"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.08424","article-title":"Long-term forecasting with tide: time-series dense encoder","author":"Das","year":"2023","journal-title":"arXiv"},{"key":"B7","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1016\/j.ijforecast.2010.02.015","article-title":"Mixture of mlp-experts for trend forecasting of time series: A case study of the tehran stock exchange","volume":"27","author":"Ebrahimpour","year":"2011","journal-title":"Int. J. Forecast"},{"key":"B8","doi-asserted-by":"publisher","first-page":"31957","DOI":"10.5555\/3600270.3602586","article-title":"Factored adaptation for non-stationary reinforcement learning","volume":"35","author":"Feng","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3483596","article-title":"Neural network-based financial volatility forecasting: a systematic review","volume":"55","author":"Ge","year":"2022","journal-title":"ACM Comp. Surv"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.00752","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv"},{"key":"B11","first-page":"1474","article-title":"Hippo: recurrent memory with optimal polynomial projections","volume":"33","author":"Gu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B12","first-page":"35971","article-title":"On the parameterization and initialization of diagonal state space models","volume":"35","author":"Gu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2111.00396","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"","journal-title":"arXiv"},{"key":"B14","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"","journal-title":"arXiv"},{"key":"B15","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"","journal-title":"arXiv"},{"key":"B16","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume":"34","author":"Gu","year":"","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B17","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume":"34","author":"Gu","year":"","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s13677-023-00576-7","article-title":"Time series forecasting model for non-stationary series pattern extraction using deep learning and garch modeling","volume":"13","author":"Han","year":"2024","journal-title":"J. Cloud Comp"},{"key":"B19","doi-asserted-by":"publisher","first-page":"3961","DOI":"10.3390\/app10113961","article-title":"Predicting the trend of stock market index using the hybrid neural network based on multiple time scale feature learning","volume":"10","author":"Hao","year":"2020","journal-title":"Appl. Sci"},{"key":"B20","first-page":"e17847","article-title":"Sustainable energy solutions: Innovations and challenges","volume":"9","author":"Johnson","year":"2023","journal-title":"Heliyon"},{"key":"B21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.32604\/jbd.2023.046223","article-title":"Explainable ai for time series forecasting: a survey","volume":"11","author":"Khan","year":"2024","journal-title":"J. Big Data"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2001.04451","article-title":"Reformer: the efficient transformer","author":"Kitaev","year":"2020","journal-title":"arXiv"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1716","DOI":"10.1108\/BPMJ-12-2023-0953","article-title":"Business process management in the era of digital transformation","volume":"30","author":"Kumar","year":"2023","journal-title":"Bus. Process Manage. J"},{"key":"B25","doi-asserted-by":"publisher","first-page":"2322","DOI":"10.3390\/app10072322","article-title":"Temporal convolutional networks applied to energy-related time series forecasting","volume":"10","author":"Lara-Ben\u00edtez","year":"2020","journal-title":"Appl. Sci"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.00235","article-title":"Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting","author":"Li","year":"2019","journal-title":"arXiv"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.15772","article-title":"Bi-Mamba+: bidirectional mamba for time series forecasting","author":"Liang","year":"2024","journal-title":"arXiv"},{"key":"B28","first-page":"1565287","article-title":"Advancements in natural language processing: a review","volume":"8","author":"Liu","year":"2025","journal-title":"Fronti. Artif. Intellig"},{"key":"B29","doi-asserted-by":"publisher","first-page":"5816","DOI":"10.48550\/arXiv.2106.09305","article-title":"Scinet: Time series modeling and forecasting with sample convolution and interaction","volume":"35","author":"Liu","year":"","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B30","article-title":"\u201cPyraformer: low-complexity pyramidal attention for long-range time series modeling and forecasting,\u201d","author":"Liu","year":"","journal-title":"International Conference on Learning Representations (ICLR 2022), Virtual Conference (OpenReview)"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.06625","article-title":"iTransformer: inverted transformers are effective for time series forecasting","author":"Liu","year":"","journal-title":"arXiv"},{"key":"B32","article-title":"iTransformer: inverted transformers are effective for time series forecasting","author":"Liu","year":"","journal-title":"arXiv"},{"key":"B33","doi-asserted-by":"publisher","first-page":"e12633","DOI":"10.1111\/exsy.12633","article-title":"A hybrid model for financial time-series forecasting based on mixed methodologies","volume":"38","author":"Luo","year":"2021","journal-title":"Expert Syst"},{"key":"B34","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1109\/IPDPSW.2018.00091","article-title":"\u201cNVIDIA tensor core programmability, performance & precision,\u201d","volume-title":"2018 IEEE international parallel and distributed processing symposium workshops (IPDPSW)","author":"Markidis","year":"2018"},{"key":"B35","first-page":"1444891","article-title":"Human-AI collaboration: Enhancing productivity and creativity","volume":"8","author":"Nguyen","year":"2025","journal-title":"Front. Artif. Intellig"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.01703","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"arXiv"},{"key":"B37","first-page":"3","article-title":"Machine learning techniques in financial forecasting","volume":"10","author":"Patel","year":"2023","journal-title":"J. Financ. Eng"},{"key":"B38","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":"Comp. Econ"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1549209","DOI":"10.3389\/fenvs.2025.1549209","article-title":"Sfdformer: a frequency-based sparse decomposition transformer for air pollution time series prediction","volume":"13","author":"Qin","year":"2025","journal-title":"Front. Environm. Sci"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1016\/j.ijforecast.2019.07.001","article-title":"Deepar: Probabilistic forecasting with autoregressive recurrent networks","volume":"36","author":"Salinas","year":"2020","journal-title":"Int. J. Forecast"},{"key":"B41","doi-asserted-by":"publisher","first-page":"106181","DOI":"10.1016\/j.asoc.2020.106181","article-title":"Financial time series forecasting with deep learning: a systematic literature review: 2005-2019","volume":"90","author":"Sezer","year":"2020","journal-title":"Appl. Soft Comput"},{"key":"B42","doi-asserted-by":"publisher","first-page":"101669","DOI":"10.1016\/j.frl.2020.101669","article-title":"Covid-19's disasters are perilous than global financial crisis: a rumor or fact?","volume":"36","author":"Shehzad","year":"2020","journal-title":"Finance Res. Letters"},{"key":"B43","first-page":"1290491","article-title":"Ethical considerations in ai-powered decision making","volume":"7","author":"Smith","year":"2024","journal-title":"Front. Artif. Intellig"},{"key":"B44","doi-asserted-by":"publisher","first-page":"121527","DOI":"10.1016\/j.eswa.2023.121527","article-title":"Modelling and forecasting high-frequency data with jumps based on a hybrid nonparametric regression and lstm model","volume":"237","author":"Song","year":"2024","journal-title":"Expert Syst. Appl"},{"key":"B45","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1089\/big.2020.0159","article-title":"Deep learning for time series forecasting: a survey","volume":"9","author":"Torres","year":"2021","journal-title":"Big Data"},{"key":"B46","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1007\/978-3-030-76124-0_7","article-title":"\u201cThe state space model in finance,\u201d","volume-title":"Bayesian Inference of State Space Models: Kalman Filtering and Beyond","author":"Triantafyllopoulos","year":"2021"},{"key":"B47","doi-asserted-by":"publisher","first-page":"129178","DOI":"10.1016\/j.neucom.2024.129178","article-title":"Is mamba effective for time series forecasting?","volume":"619","author":"Wang","year":"2025","journal-title":"Neurocomputing"},{"key":"B48","first-page":"22419","article-title":"Autoformer: decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B49","doi-asserted-by":"publisher","first-page":"12979","DOI":"10.1007\/s10489-024-05789-0","article-title":"Long short-term temporal fusion transformer for short-term forecasting of limit order book in china markets","volume":"54","author":"Wu","year":"2024","journal-title":"Appl. Intellig"},{"key":"B50","doi-asserted-by":"publisher","first-page":"110356","DOI":"10.1016\/j.asoc.2023.110356","article-title":"Stock index forecasting based on multivariate empirical mode decomposition and temporal convolutional networks","volume":"142","author":"Yao","year":"2023","journal-title":"Appl. Soft Comput"},{"key":"B51","doi-asserted-by":"publisher","first-page":"46241","DOI":"10.1109\/ACCESS.2024.3381500","article-title":"Long-term interbank bond rate prediction based on iceemdan and machine learning","volume":"12","author":"Yu","year":"2024","journal-title":"IEEE Access"},{"key":"B52","doi-asserted-by":"publisher","first-page":"11121","DOI":"10.1609\/aaai.v37i9.26317","article-title":"Are transformers effective for time series forecasting?","volume":"37","author":"Zeng","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intellig"},{"key":"B53","doi-asserted-by":"publisher","first-page":"109584","DOI":"10.1016\/j.knosys.2022.109584","article-title":"Muformer: A long sequence time-series forecasting model based on modified multi-head attention","volume":"254","author":"Zeng","year":"2022","journal-title":"Knowl.-Based Syst"},{"key":"B54","doi-asserted-by":"publisher","first-page":"2620","DOI":"10.3390\/rs16142620","article-title":"Remote sensing applications in urban planning: A case study","volume":"16","author":"Zhang","year":"2024","journal-title":"Remote Sens"},{"key":"B55","doi-asserted-by":"publisher","first-page":"347","DOI":"10.3390\/math13030347","article-title":"Major issues in high-frequency financial data analysis: a survey of solutions","volume":"13","author":"Zhang","year":"2025","journal-title":"Mathematics"},{"key":"B56","doi-asserted-by":"publisher","first-page":"11106","DOI":"10.1609\/aaai.v35i12.17325","article-title":"Informer: Beyond efficient transformer for long sequence time-series forecasting","volume":"35","author":"Zhou","year":"2021","journal-title":"Proc. AAAI conf. Artif. Intellig"},{"key":"B57","first-page":"27268","article-title":"\u201cFEDformer: Frequency enhanced decomposed transformer for long-term series forecasting,\u201d","volume-title":"International Conference on Machine Learning","author":"Zhou","year":"2022"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1599799\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T05:25:17Z","timestamp":1752557117000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1599799\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,15]]},"references-count":57,"alternative-id":["10.3389\/frai.2025.1599799"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1599799","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,15]]},"article-number":"1599799"}}