{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T02:06:03Z","timestamp":1776477963653,"version":"3.51.2"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:00:00Z","timestamp":1742947200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:00:00Z","timestamp":1742947200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003385","name":"Georg-August-Universit\u00e4t G\u00f6ttingen","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003385","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003385","name":"Georg-August-Universit\u00e4t G\u00f6ttingen","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003385","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The stock market is characterized by its high nonlinearity and complexity, making traditional methods ineffective in capturing its nonlinear features and complex market dynamics. This paper proposes a novel stock price forecasting model\u2014the Variational Mode Decomposition\u2014Triangulated Maximally Filtered Graph\u2014Long Short-Term Memory (VMD\u2013TMFG\u2013LSTM) combined model\u2014aimed at improving prediction accuracy, stability, and computational efficiency. The proposed model first employs Variational Mode Decomposition (VMD) to decompose the stock price time series into multiple smooth intrinsic mode functions (IMFs), reducing data complexity and mitigating noise interference. Subsequently, the TMFG algorithm is utilized for feature selection, simplifying the input data and accelerating the iterative convergence process. Finally, the filtered features are modeled and predicted using a Long Short-Term Memory (LSTM) network. Experimental results demonstrate that the VMD\u2013TMFG\u2013LSTM model significantly outperforms AutoRegressive Integrated Moving Average (ARIMA), Neural Network (NN), Deep Neural Network (DNN), Convolutional Neural Network (CNN), as well as single LSTM, TMFG\u2013LSTM, and VMD\u2013LSTM models in forecasting the closing prices of multiple stocks. Specifically, for Shanghai International Airport Co., Ltd. (sh600009), the VMD\u2013TMFG\u2013LSTM model achieves a 69.76% reduction in Root Mean Squared Error (RMSE), a 71.41% reduction in Mean Absolute Error (MAE), a 46.28% reduction in runtime, and an improvement of 0.2184 in R-squared (R<jats:sup>2<\/jats:sup>), indicating significantly higher prediction accuracy. In conclusion, the combined model proposed in this paper enhances the accuracy, efficiency, and stability of stock price prediction, providing a robust and efficient solution for forecasting stock market trends.<\/jats:p>","DOI":"10.1186\/s40537-025-01127-4","type":"journal-article","created":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T08:57:47Z","timestamp":1742979467000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Multi-feature stock price prediction by LSTM networks based on VMD and TMFG"],"prefix":"10.1186","volume":"12","author":[{"given":"Zhixin","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Qingyang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yanrong","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Hongjiu","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,26]]},"reference":[{"key":"1127_CR1","doi-asserted-by":"crossref","unstructured":"Aseeri AO. Effective short-term forecasts of Saudi stock price trends using technical indicators and large-scale multivariate time series. PeerJ Comput Sci. 2023;9.","DOI":"10.7717\/peerj-cs.1205"},{"key":"1127_CR2","unstructured":"Hansen JIZ. Triple exponential smoothing: a tool for common stock price prediction. 1970."},{"key":"1127_CR3","doi-asserted-by":"crossref","unstructured":"Yang H-L, Lin H-C. An integrated model combined ARIMA, EMD with SVR for stock indices forecasting. Int J Artif Intell Tools. 2016;25(2).","DOI":"10.1142\/S0218213016500056"},{"issue":"2","key":"1127_CR4","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1007\/s00521-021-05903-0","volume":"34","author":"W Serrano","year":"2022","unstructured":"Serrano W. The random neural network in price predictions. Neural Comput Appl. 2022;34(2):855\u201373.","journal-title":"Neural Comput Appl"},{"issue":"1","key":"1127_CR5","first-page":"5","volume":"46","author":"R Bourbonnais","year":"2012","unstructured":"Bourbonnais R, Maftei MM. ARFIMA process: tests and applications at a white noise process, a random walk process and the stock exchange index CAC 40. Econ Comput Econ Cybern Stud Res. 2012;46(1):5\u201316.","journal-title":"Econ Comput Econ Cybern Stud Res"},{"key":"1127_CR6","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1016\/j.physa.2014.05.047","volume":"410","author":"G Prat-Ortega","year":"2014","unstructured":"Prat-Ortega G, Savel\u2019ev SE. Stochastic GARCH dynamics describing correlations between stocks. Phys A Stat Mech Appl. 2014;410:623\u20137.","journal-title":"Phys A Stat Mech Appl"},{"key":"1127_CR7","first-page":"S143","volume":"22","author":"JNK Liu","year":"2013","unstructured":"Liu JNK, Hu Y. Application of feature-weighted support vector regression using grey correlation degree to stock price forecasting. Neural Comput Appl. 2013;22:S143\u201352.","journal-title":"Neural Comput Appl"},{"key":"1127_CR8","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.datak.2018.08.003","volume":"118","author":"W Chen","year":"2018","unstructured":"Chen W, et al. Leveraging social media news to predict stock index movement using RNN-boost. Data Knowl Eng. 2018;118:14\u201324.","journal-title":"Data Knowl Eng"},{"key":"1127_CR9","doi-asserted-by":"crossref","unstructured":"Cao J, Wang J. Stock price forecasting model based on modified convolution neural network and financial time series analysis. Int J Commun Syst. 2019;32(12).","DOI":"10.1002\/dac.3987"},{"issue":"06","key":"1127_CR10","doi-asserted-by":"crossref","first-page":"620","DOI":"10.21078\/JSSI-2022-620-13","volume":"10","author":"Y Sun","year":"2022","unstructured":"Sun Y, Sun Q, Zhu S. Prediction of Shanghai stock index based on investor sentiment and CNN-LSTM model. J Syst Sci Inf. 2022;10(06):620\u201332.","journal-title":"J Syst Sci Inf"},{"key":"1127_CR11","unstructured":"Gao QZ. Stock market forecasting using recurrent neural network. 2016"},{"issue":"9","key":"1127_CR12","doi-asserted-by":"crossref","first-page":"1507","DOI":"10.1080\/14697688.2019.1622287","volume":"19","author":"S Chen","year":"2019","unstructured":"Chen S, Ge L. Exploring the attention mechanism in LSTM-based Hong Kong stock price movement prediction. Quant Finance. 2019;19(9):1507\u201315.","journal-title":"Quant Finance"},{"issue":"9","key":"1127_CR13","doi-asserted-by":"crossref","first-page":"11768","DOI":"10.1007\/s11227-022-04326-5","volume":"78","author":"L Tian","year":"2022","unstructured":"Tian L, et al. Stock price prediction based on LSTM and LightGBM hybrid model. J Supercomput. 2022;78(9):11768\u201393.","journal-title":"J Supercomput"},{"key":"1127_CR14","doi-asserted-by":"crossref","unstructured":"Srijiranon K, Lertratanakham Y, Tanantong T. A hybrid framework using PCA, EMD and LSTM methods for stock market price prediction with sentiment analysis. Appl Sci-Basel. 2022;12(21).","DOI":"10.3390\/app122110823"},{"issue":"12","key":"1127_CR15","doi-asserted-by":"crossref","first-page":"4296","DOI":"10.1007\/s10489-020-01814-0","volume":"50","author":"H Niu","year":"2020","unstructured":"Niu H, Xu K, Wang W. A hybrid stock price index forecasting model based on variational mode decomposition and LSTM network. Appl Intell. 2020;50(12):4296\u2013309.","journal-title":"Appl Intell"},{"issue":"6","key":"1127_CR16","doi-asserted-by":"crossref","first-page":"10511","DOI":"10.3233\/JIFS-221919","volume":"44","author":"H Li","year":"2023","unstructured":"Li H, Hu Y, Liu H. A novel LASSO-ATT-LSTM model of stock price prediction based on multi-source heterogeneous data. J Intell Fuzzy Syst. 2023;44(6):10511\u201321.","journal-title":"J Intell Fuzzy Syst"},{"key":"1127_CR17","doi-asserted-by":"crossref","unstructured":"Chen X, et al. A multi-feature stock price prediction model based on multi-feature calculation, LASSO feature selection, and Ca-LSTM network. Connecti Sci. 2024;36(1).","DOI":"10.1080\/09540091.2023.2286188"},{"key":"1127_CR18","doi-asserted-by":"publisher","unstructured":"Wu DM, Wang XL, Wu SC. A hybrid method based on extreme learning machine and wavelet transform denoising for stock prediction. Entropy. 2021;23(4):Article 440. https:\/\/doi.org\/10.3390\/e23040440","DOI":"10.3390\/e23040440"},{"key":"1127_CR19","doi-asserted-by":"publisher","unstructured":"Liu ZC, et al. Option pricing using stochastic volatility model under Fourier transform of nonlinear differential equation. Fractals-Complex Geom Patterns Scaling in Nat Soc. 2022;30(02):Article 2240065. https:\/\/doi.org\/10.1142\/S0218348X22400655","DOI":"10.1142\/S0218348X22400655"},{"issue":"1","key":"1127_CR20","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.physa.2006.04.019","volume":"370","author":"T Aste","year":"2006","unstructured":"Aste T, Di Matteo T. Dynamical networks from correlations. Phys A Stat Mech Appl. 2006;370(1):156\u201361.","journal-title":"Phys A Stat Mech Appl"},{"issue":"2","key":"1127_CR21","first-page":"161","volume":"5","author":"GP Massara","year":"2017","unstructured":"Massara GP, Di Matteo T, Aste T. Network filtering for big data: triangulated maximally filtered graph. J Complex Netw. 2017;5(2):161\u201378.","journal-title":"J Complex Netw"},{"issue":"6","key":"1127_CR22","doi-asserted-by":"crossref","first-page":"12329","DOI":"10.3233\/JIFS-232479","volume":"45","author":"Q Liu","year":"2023","unstructured":"Liu Q, Yahyapour R. Forecast stock price based on GRA-LoGo model of information filtering networks. J Intell Fuzzy Syst. 2023;45(6):12329\u201339.","journal-title":"J Intell Fuzzy Syst"},{"key":"1127_CR23","doi-asserted-by":"publisher","unstructured":"Briola A, Aste T. Dependency structures in cryptocurrency market from high to low frequency. Entropy. 2022;24(11):Article 1548. https:\/\/doi.org\/10.3390\/e24111548","DOI":"10.3390\/e24111548"},{"issue":"6","key":"1127_CR24","doi-asserted-by":"crossref","first-page":"211","DOI":"10.5547\/01956574.44.6.ssha","volume":"44","author":"SJ Hussain Shahzad","year":"2023","unstructured":"Hussain Shahzad SJ, Ferrer R, Bouri E. Systemic risk in the global energy sector: structure, determinants and portfolio management implications. Energy J. 2023;44(6):211\u201343.","journal-title":"Energy J"},{"issue":"6\u20131","key":"1127_CR25","volume":"94","author":"W Barfuss","year":"2016","unstructured":"Barfuss W, et al. Parsimonious modeling with information filtering networks. Phys Rev E. 2016;94(6\u20131): 062306.","journal-title":"Phys Rev E"},{"key":"1127_CR26","doi-asserted-by":"crossref","unstructured":"Xiao F, et al. VMD-based denoising methods for surface electromyography signals. J Neural Eng. 2019;16(5).","DOI":"10.1088\/1741-2552\/ab33e4"},{"key":"1127_CR27","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.watres.2016.05.002","volume":"100","author":"Y-D Kim","year":"2016","unstructured":"Kim Y-D, et al. A novel integrated thermal-\/membrane-based solar energy-driven hybrid desalination system: concept description and simulation results. Water Res. 2016;100:7\u201319.","journal-title":"Water Res"},{"key":"1127_CR28","doi-asserted-by":"crossref","unstructured":"Yuan X, et al. Prediction interval of wind power using parameter optimized Beta distribution-based LSTM model. Appl Soft Comput. 2019;82.","DOI":"10.1016\/j.asoc.2019.105550"},{"key":"1127_CR29","doi-asserted-by":"crossref","unstructured":"Yang G, et al. Method and validation of coal mine gas concentration prediction by integrating PSO algorithm and LSTM network. Processes. 2024;12(5).","DOI":"10.3390\/pr12050898"},{"key":"1127_CR30","doi-asserted-by":"crossref","unstructured":"Lee M-C. Research on the feasibility of applying GRU and attention mechanism combined with technical indicators in stock trading strategies. Appl Sci-Basel. 2022;12(3).","DOI":"10.3390\/app12031007"},{"issue":"2","key":"1127_CR31","doi-asserted-by":"crossref","first-page":"401","DOI":"10.2298\/CSIS200301002L","volume":"18","author":"M-C Lee","year":"2021","unstructured":"Lee M-C, et al. Exploring the effectiveness of deep neural networks with technical analysis applied to stock market prediction. Comput Sci Inf Syst. 2021;18(2):401\u201318.","journal-title":"Comput Sci Inf Syst"},{"key":"1127_CR32","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1016\/j.sigpro.2016.02.011","volume":"125","author":"Y Liu","year":"2016","unstructured":"Liu Y, et al. Variational mode decomposition denoising combined with detrended fluctuation analysis. Signal Process. 2016;125:349\u201364.","journal-title":"Signal Process"},{"key":"1127_CR33","doi-asserted-by":"crossref","unstructured":"Liu B, et al. Research on leak location method of water supply pipeline based on negative pressure wave technology and VMD algorithm. Measurement. 2021;186.","DOI":"10.1016\/j.measurement.2021.110235"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-025-01127-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-025-01127-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-025-01127-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T08:58:35Z","timestamp":1742979515000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-025-01127-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,26]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1127"],"URL":"https:\/\/doi.org\/10.1186\/s40537-025-01127-4","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,26]]},"assertion":[{"value":"21 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Zhixin Zhang, Qingyang Liu, Yanrong Hu and Hongjiu Liu declare that there is no conflict of interests regarding the publication of our paper \u201cMulti-feature stock price prediction by LSTM networks based on VMD and TMFG\u201d.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Qingyang Liu, Yanrong Hu and Hongjiu Liu are the joint first authors and co-corresponding authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}}],"article-number":"74"}}