{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:40:13Z","timestamp":1777696813798,"version":"3.51.4"},"reference-count":66,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T00:00:00Z","timestamp":1738281600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["2022R1F1A1066744"],"award-info":[{"award-number":["2022R1F1A1066744"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["2022R1G1A1011756"],"award-info":[{"award-number":["2022R1G1A1011756"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Intelligent Data Analysis: An International Journal"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:p>Due to recent developments in deep learning models, the field of time series forecasting has undergone significant advancements related to forecasting accuracy and reliability across various industrial sectors. Unfortunately, traditional deep learning models often encounter long-term and multivariate forecasting challenges due to complex temporal patterns. To overcome this, decomposition-based approaches have been proposed. However, there have been few attempts to utilize an appropriate network type for each decomposed component. In this paper, we propose the two-stage decomposition-based hybrid deep neural network (TSDNet) for enhancing the accuracy of long-term time series forecasting. To effectively manage complicated time series data with varying periodicities, TSDNet accommodates a single linear layer for forecasting smooth trend components and a convolutional module for complex seasonal components. Extensive experiments on various benchmark and real-world financial datasets show that TSDNet mostly improves the forecasting accuracy compared to the existing methods considered, particularly in long-term forecasting scenarios. Furthermore, ablation studies were conducted to examine the impact of the number of decomposition stages and the implementation of different modules on the decomposed elements, suggesting the effectiveness of the proposed approach.<\/jats:p>","DOI":"10.1177\/1088467x241308796","type":"journal-article","created":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T05:19:16Z","timestamp":1738300756000},"page":"1399-1418","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":2,"title":["TSDNet: A two-stage decomposition-based hybrid deep neural network for long-term time series forecasting"],"prefix":"10.1177","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6556-2220","authenticated-orcid":false,"given":"Sukhyun","family":"Cho","sequence":"first","affiliation":[{"name":"Department of Industrial Engineering and Institute for Industrial Systems Innovation, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5636-2743","authenticated-orcid":false,"given":"Dokyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Institute for Industrial Systems Innovation, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonghun","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Institute for Industrial Systems Innovation, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8890-7381","authenticated-orcid":false,"given":"In-Beom","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Industrial and Management Engineering, Myongji University, Yongin, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,1,31]]},"reference":[{"key":"e_1_3_4_2_2","unstructured":"Gao J. Machine learning applications for data center optimization. 2014."},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2960844"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-019-2561-z"},{"key":"e_1_3_4_5_2","doi-asserted-by":"crossref","unstructured":"Sawhney R Agarwal S Wadhwa A et\u00a0al. Deep attentive learning for stock movement prediction from social media text and company correlations. In: Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP). 2020 pp.8415\u20138426.","DOI":"10.18653\/v1\/2020.emnlp-main.676"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2020.0209"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106889"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2018.11.061"},{"key":"e_1_3_4_9_2","volume-title":"Time series analysis: forecasting and control","author":"Box GE","year":"2015","unstructured":"Box GE, Jenkins GM, Reinsel GC, et al. Time series analysis: forecasting and control. Hoboken, NJ: John Wiley & Sons, 2015."},{"key":"e_1_3_4_10_2","doi-asserted-by":"crossref","unstructured":"Kusuma J Doherty L Ramchandran K. Distributed compression for sensor networks. In: Proceedings 2001 international conference on image processing (Cat. No. 01CH37205) 2021 vol.1 pp.82\u201385. IEEE.","DOI":"10.1109\/ICIP.2001.958958"},{"key":"e_1_3_4_11_2","unstructured":"Goodfellow IJ Shlens J Szegedy C. Explaining and harnessing adversarial examples. arXiv preprint arXiv:14126572 2014."},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3107975"},{"key":"e_1_3_4_13_2","unstructured":"Wen Q Zhou T Zhang C et\u00a0al. Transformers in time series: a survey. arXiv preprint arXiv:220207125 2022."},{"key":"e_1_3_4_14_2","first-page":"4837","article-title":"Think globally, act locally: a deep neural network approach to high-dimensional time series forecasting","volume":"32","author":"Sen R","year":"2019","unstructured":"Sen R, Yu HF, Dhillon IS. Think globally, act locally: a deep neural network approach to high-dimensional time series forecasting. In: Proceedings of the international conference on neural information processing systems (NeurIPS), 2019, vol.32, Article No. 435, pp.4837\u20134846.","journal-title":"Proceedings of the international conference on neural information processing systems (NeurIPS)"},{"key":"e_1_3_4_15_2","unstructured":"Li Z Qi S Li Y et\u00a0al. Revisiting long-term time series forecasting: an investigation on linear mapping. arXiv preprint arXiv:230510721 2023."},{"key":"e_1_3_4_16_2","unstructured":"Bai S Kolter JZ Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:180301271 2018."},{"key":"e_1_3_4_17_2","unstructured":"Wu H Hu T Liu Y et\u00a0al. Timesnet: Temporal 2d-variation modeling for general time series analysis. In: Proceedings of the international conference on learning representations (ICLR) 2023."},{"key":"e_1_3_4_18_2","first-page":"3","article-title":"Stl: a seasonal-trend decomposition","volume":"6","author":"Cleveland RB","year":"1990","unstructured":"Cleveland RB, Cleveland WS, McRae JE, et\u00a0al. Stl: a seasonal-trend decomposition. J\u00a0Off Stat 1990; 6: 3\u201373.","journal-title":"J\u00a0Off Stat"},{"key":"e_1_3_4_19_2","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu H","year":"2021","unstructured":"Wu H, Xu J, Wang J, et\u00a0al. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Adv Neural Inf Process Syst 2021; 34: 22419\u201322430.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_20_2","unstructured":"Wang H Peng J Huang F et\u00a0al. Micn: Multi-scale local and global context modeling for long-term series forecasting. In: International conference on learning representations (ICLR) 2023."},{"key":"e_1_3_4_21_2","doi-asserted-by":"crossref","unstructured":"Zeng A Chen M Zhang L et\u00a0al. Are transformers effective for time series forecasting? In: Proceedings of the AAAI conference on artificial intelligence volume 37. 2023 pp.11121\u201311128.","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1002\/for.3980040103"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2015.06.022"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932254"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2019.112656"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116772"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_4_28_2","doi-asserted-by":"crossref","unstructured":"Cho K Van Merri\u00ebnboer B Gulcehre C et\u00a0al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:14061078 2014.","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_4_29_2","doi-asserted-by":"crossref","unstructured":"Qin Y Song D Chen H et\u00a0al. A dual-stage attention-based recurrent neural network for time series prediction. arXiv preprint arXiv:170402971 2017.","DOI":"10.24963\/ijcai.2017\/366"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.113082"},{"key":"e_1_3_4_31_2","first-page":"73","article-title":"Dilated convolutional neural networks for time series forecasting","volume":"22","author":"Borovykh A","year":"2019","unstructured":"Borovykh A, Bohte S, Oosterlee CW. Dilated convolutional neural networks for time series forecasting. J Comput Finance Forth 2019; 22: 73\u2013101.","journal-title":"J Comput Finance Forth"},{"key":"e_1_3_4_32_2","doi-asserted-by":"crossref","unstructured":"Huang S Wang D Wu X et\u00a0al. Dsanet: dual self-attention network for multivariate time series forecasting. In: Proceedings of the 28th ACM international conference on information and knowledge management 2019 pp.2129\u20132132.","DOI":"10.1145\/3357384.3358132"},{"key":"e_1_3_4_33_2","first-page":"5816","article-title":"Scinet: time series modeling and forecasting with sample convolution and interaction","volume":"35","author":"Liu M","year":"2022","unstructured":"Liu M, Zeng A, Chen M, et\u00a0al. Scinet: time series modeling and forecasting with sample convolution and interaction. Adv Neural Inf Process Syst 2022; 35: 5816\u20135828.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120246"},{"key":"e_1_3_4_35_2","first-page":"1","article-title":"Temperature forecasting via convolutional recurrent neural networks based on time-series data","volume":"2020","author":"Zhang Z","year":"2020","unstructured":"Zhang Z, Dong Y. Temperature forecasting via convolutional recurrent neural networks based on time-series data. Complexity 2020; 2020: 1\u20138.","journal-title":"Complexity"},{"key":"e_1_3_4_36_2","doi-asserted-by":"crossref","unstructured":"Lai G Chang WC Yang Y et\u00a0al. Modeling long-and short-term temporal patterns with deep neural networks. In: The 41st international ACM SIGIR conference on research & development in information retrieval 2018 pp.95\u2013104.","DOI":"10.1145\/3209978.3210006"},{"key":"e_1_3_4_37_2","unstructured":"Chang YY Sun FY Wu YH et\u00a0al. A memory-network based solution for multivariate time-series forecasting. arXiv preprint arXiv:180902105 2018."},{"key":"e_1_3_4_38_2","unstructured":"Gu A Goel K R\u00e9 C. Efficiently modeling long sequences with structured state spaces. In: ICLR 2022."},{"key":"e_1_3_4_39_2","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani A","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. Proceedings of International Conference on Neural Information Processing Systems (NIPS), 2017; 30: 6000\u20136010.","journal-title":"Proceedings of International Conference on Neural Information Processing Systems (NIPS),"},{"key":"e_1_3_4_40_2","first-page":"5243","article-title":"Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting","volume":"32","author":"Li S","year":"2019","unstructured":"Li S, Jin X, Xuan Y, et al. Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. In: Proceedings of the international conference on neural information processing systems (NeurIPS), 2019, vol.32, Article No. 471, pp.5243\u20135253.","journal-title":"Proceedings of the international conference on neural information processing systems (NeurIPS)"},{"key":"e_1_3_4_41_2","unstructured":"Kitaev N Kaiser \u0141 Levskaya A et\u00a0al. Reformer: the efficient transformer. In: ICLR 2020."},{"key":"e_1_3_4_42_2","doi-asserted-by":"crossref","unstructured":"Zhou H Zhang S Peng J et\u00a0al. Informer: Beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of the AAAI conference on artificial intelligence Vol.35 2021 pp.11106\u201311115.","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_3_4_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2021.03.012"},{"key":"e_1_3_4_44_2","unstructured":"Liu S Yu H Liao C et\u00a0al. Pyraformer: low-complexity pyramidal attention for long-range time series modeling and forecasting. In: International conference on learning representations 2022."},{"key":"e_1_3_4_45_2","unstructured":"Woo G Liu C Sahoo D et\u00a0al. Etsformer: exponential smoothing transformers for time-series forecasting. arXiv preprint arXiv:220201381 2022."},{"key":"e_1_3_4_46_2","doi-asserted-by":"crossref","unstructured":"Chowdhury RR Zhang X Shang J et\u00a0al. Tarnet: task-aware reconstruction for time-series transformer. In: Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data Mining. 2022 pp.212\u2013220.","DOI":"10.1145\/3534678.3539329"},{"key":"e_1_3_4_47_2","unstructured":"Liu Y Wu H Wang J et\u00a0al. Non-stationary transformers: exploring the stationarity in time series forecasting. In Oh AH Agarwal A Belgrave D et\u00a0al. (eds.) Advances in neural information processing systems. 2022 https:\/\/openreview.net\/forum?id=ucNDIDRNjjv."},{"key":"e_1_3_4_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106042"},{"key":"e_1_3_4_49_2","unstructured":"Liu Y Hu T Zhang H et\u00a0al. itransformer: inverted transformers are effective for time series forecasting. In: International conference on learning representations (ICLR) 2024."},{"key":"e_1_3_4_50_2","unstructured":"Oreshkin BN Carpov D Chapados N et\u00a0al. N-beats: Neural basis expansion analysis for interpretable time series forecasting. In: International conference on learning representations 2020 https:\/\/openreview.net\/forum?id=r1ecqn4YwB."},{"key":"e_1_3_4_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2022.03.001"},{"key":"e_1_3_4_52_2","first-page":"6989","article-title":"Nhits: Neural hierarchical interpolation for time series forecasting","volume":"37","author":"Challu C","year":"2023","unstructured":"Challu C, Olivares KG, Oreshkin BN, et\u00a0al. Nhits: Neural hierarchical interpolation for time series forecasting. Proc AAAI Conf Artif Intell 2023; 37: 6989\u20136997.","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"e_1_3_4_53_2","unstructured":"Zhang T Zhang Y Cao W et\u00a0al. Less is more: fast multivariate time series forecasting with light sampling-oriented MLP structures. arXiv preprint arXiv:220701186 2022."},{"key":"e_1_3_4_54_2","doi-asserted-by":"crossref","unstructured":"Korvesis P Besseau S Vazirgiannis M. Predictive maintenance in aviation: failure prediction from post-flight reports. In: 2018 IEEE 34th International conference on data engineering (ICDE). IEEE 2018 pp.1414\u20131422.","DOI":"10.1109\/ICDE.2018.00160"},{"key":"e_1_3_4_55_2","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2016.0871"},{"key":"e_1_3_4_56_2","doi-asserted-by":"crossref","unstructured":"Wang J Wang Z Li J et\u00a0al. Multilevel wavelet decomposition network for interpretable time series analysis. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining 2018 pp.2437\u20132446.","DOI":"10.1145\/3219819.3220060"},{"key":"e_1_3_4_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.105963"},{"key":"e_1_3_4_58_2","unstructured":"Zhou T Ma Z Wen Q et\u00a0al. Fedformer: frequency enhanced decomposed transformer for long-term series forecasting. In: International conference on machine learning. PMLR 2022 pp. 27268\u201327286."},{"key":"e_1_3_4_59_2","unstructured":"Woo G Liu C Sahoo D et\u00a0al. CoST: contrastive learning of disentangled seasonal-trend representations for time series forecasting. In: International conference on learning representations 2022 https:\/\/openreview.net\/forum?id=PilZY3omXV2."},{"key":"e_1_3_4_60_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121642"},{"key":"e_1_3_4_61_2","unstructured":"Kim T Kim J Tae Y et\u00a0al. Reversible instance normalization for accurate time-series forecasting against distribution shift. In: International conference on learning representations 2022 https:\/\/openreview.net\/forum?id=cGDAkQo1C0p."},{"key":"e_1_3_4_62_2","doi-asserted-by":"crossref","unstructured":"Ogasawara E Martinez LC De Oliveira D et\u00a0al. Adaptive normalization: a novel data normalization approach for non-stationary time series. In: The 2010 international joint conference on neural networks (IJCNN). IEEE 2010 pp.1\u20138.","DOI":"10.1109\/IJCNN.2010.5596746"},{"key":"e_1_3_4_63_2","volume-title":"Mathematics of the discrete Fourier transform (DFT): with audio applications","author":"Smith JO","year":"2008","unstructured":"Smith JO. Mathematics of the discrete Fourier transform (DFT): with audio applications. Stanford, CA: Julius Smith, 2008."},{"key":"e_1_3_4_64_2","doi-asserted-by":"crossref","unstructured":"Szegedy C Liu W Jia Y et\u00a0al. Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition 2015 pp.1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_4_65_2","unstructured":"Kingma D Ba J. Adam: A Method for Stochastic Optimization. In: International conference on learning representations (ICLR) San Diega CA USA 2015."},{"key":"e_1_3_4_66_2","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi J","year":"2011","unstructured":"Duchi J, Hazan E, Singer Y. Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 2011; 12: 2121\u20132159.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_4_67_2","doi-asserted-by":"crossref","unstructured":"Huber PJ. Robust estimation of a location parameter. In: Breakthroughs in statistics: Methodology and distribution Springer 1992. pp.492\u2013518.","DOI":"10.1007\/978-1-4612-4380-9_35"}],"container-title":["Intelligent Data Analysis: An International Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1088467X241308796","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1088467X241308796","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1088467X241308796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:21:02Z","timestamp":1777454462000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1088467X241308796"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,31]]},"references-count":66,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1177\/1088467X241308796"],"URL":"https:\/\/doi.org\/10.1177\/1088467x241308796","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,31]]}}}