{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T11:04:16Z","timestamp":1780571056931,"version":"3.54.1"},"reference-count":45,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T00:00:00Z","timestamp":1696204800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"ANID-Millennium Science Initiative Program ICN2021_004","award":["1221938"],"award-info":[{"award-number":["1221938"]}]},{"name":"ANID-Millennium Science Initiative Program ICN2021_004","award":["11190116"],"award-info":[{"award-number":["11190116"]}]},{"name":"ANID FONDECYT","award":["1221938"],"award-info":[{"award-number":["1221938"]}]},{"name":"ANID FONDECYT","award":["11190116"],"award-info":[{"award-number":["11190116"]}]},{"name":"FONDECYT","award":["1221938"],"award-info":[{"award-number":["1221938"]}]},{"name":"FONDECYT","award":["11190116"],"award-info":[{"award-number":["11190116"]}]},{"name":"Universidad de Valparaiso","award":["1221938"],"award-info":[{"award-number":["1221938"]}]},{"name":"Universidad de Valparaiso","award":["11190116"],"award-info":[{"award-number":["11190116"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Long-term dependence is an essential feature for the predictability of time series. Estimating the parameter that describes long memory is essential to describing the behavior of time series models. However, most long memory estimation methods assume that this parameter has a constant value throughout the time series, and do not consider that the parameter may change over time. In this work, we propose an automated methodology that combines the estimation methodologies of the fractional differentiation parameter (and\/or Hurst parameter) with its application to Recurrent Neural Networks (RNNs) in order for said networks to learn and predict long memory dependencies from information obtained in nonlinear time series. The proposal combines three methods that allow for better approximation in the prediction of the values of the parameters for each one of the windows obtained, using Recurrent Neural Networks as an adaptive method to learn and predict the dependencies of long memory in Time Series. For the RNNs, we have evaluated four different architectures: the Simple RNN, LSTM, the BiLSTM, and the GRU. These models are built from blocks with gates controlling the cell state and memory. We have evaluated the proposed approach using both synthetic and real-world data sets. We have simulated ARFIMA models for the synthetic data to generate several time series by varying the fractional differentiation parameter. We have evaluated the proposed approach using synthetic and real datasets using Whittle\u2019s estimates of the Hurst parameter classically obtained in each window. We have simulated ARFIMA models in such a way that the synthetic data generate several time series by varying the fractional differentiation parameter. The real-world IPSA stock option index and Tree Ringtime series datasets were evaluated. All of the results show that the proposed approach can predict the Hurst exponent with good performance by selecting the optimal window size and overlap change.<\/jats:p>","DOI":"10.3390\/make5040068","type":"journal-article","created":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T11:56:49Z","timestamp":1696247809000},"page":"1340-1358","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Predicting the Long-Term Dependencies in Time Series Using Recurrent Artificial Neural Networks"],"prefix":"10.3390","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1439-3429","authenticated-orcid":false,"given":"Cristian","family":"Ubal","sequence":"first","affiliation":[{"name":"Instituto de Estad\u00edstica, Facultad de Ciencias, Universidad de Valpara\u00edso, Valpara\u00edso 2360102, Chile"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gustavo","family":"Di-Giorgi","sequence":"additional","affiliation":[{"name":"Escuela de Administraci\u00f3n P\u00fablica, Facultad de Ciencias Econ\u00f3micas y Administrativas, Universidad de Valpara\u00edso, Valpara\u00edso 2362797, Chile"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1172-5456","authenticated-orcid":false,"given":"Javier E.","family":"Contreras-Reyes","sequence":"additional","affiliation":[{"name":"Instituto de Estad\u00edstica, Facultad de Ciencias, Universidad de Valpara\u00edso, Valpara\u00edso 2360102, Chile"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0350-6811","authenticated-orcid":false,"given":"Rodrigo","family":"Salas","sequence":"additional","affiliation":[{"name":"Escuela de Ingenier\u00eda C. Biom\u00e9dica, Facultad de Ingenier\u00eda, Universidad de Valpara\u00edso, Valpara\u00edso 2362905, Chile"},{"name":"Millennium Institute for Intelligent Healthcare Engineering (iHealth), Santiago 7820436, Chile"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,10,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Di Giorgi, G., Salas, R., Avaria, R., Ubal, C., Rosas, H., and Torres, R. (2023). Volatility Forecasting using Deep Recurrent Neural Networks as GARCH models. Comput. Stat., 1\u201327.","DOI":"10.1007\/s00180-023-01349-1"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"24232","DOI":"10.1038\/s41598-021-03650-9","article-title":"Air quality assessment and pollution forecasting using artificial neural networks in Metropolitan Lima-Peru","volume":"11","author":"Cordova","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Leite Coelho da Silva, F., da Costa, K., Canas Rodrigues, P., Salas, R., and L\u00f3pez-Gonzales, J.L. (2022). Statistical and artificial neural networks models for electricity consumption forecasting in the Brazilian industrial sector. Energies, 15.","DOI":"10.3390\/en15020588"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1007\/s00477-022-02323-x","article-title":"Deep Lagged-Wavelet for monthly rainfall forecasting in a tropical region","volume":"37","author":"Vivas","year":"2023","journal-title":"Stoch. Environ. Res. Risk Assess."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"108535","DOI":"10.1016\/j.asoc.2022.108535","article-title":"A stacking neuro-fuzzy framework to forecast runoff from distributed meteorological stations","volume":"118","author":"Querales","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kovantsev, A., and Gladilin, P. (2020, January 17\u201320). Analysis of multivariate time series predictability based on their features. Proceedings of the 2020 International Conference on Data Mining Workshops (ICDMW), Sorrento, Italy.","DOI":"10.1109\/ICDMW51313.2020.00055"},{"key":"ref_7","unstructured":"Qian, B., and Rasheed, K. (2004, January 9\u201311). Hurst exponent and financial market predictability. Proceedings of the IASTED Conference on Financial Engineering and Applications, IASTED International Conference, Cambridge, MA, USA."},{"key":"ref_8","unstructured":"Siriopoulos, C., and Markellos, R. (1996). Neural Network Model Development and Optimization. J. Comput. Intell. Financ. (Former. Neurovest J.), 7\u201313."},{"key":"ref_9","unstructured":"Siriopoulos, C., Markellos, R., and Sirlantzis, K. (1996). Applications of Artificial Neural Networks in Emerging Financial Markets, World Scientific."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1109\/72.548162","article-title":"Learning long-term dependencies in NARX recurrent neural networks","volume":"7","author":"Lin","year":"1996","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_11","first-page":"227","article-title":"Hurst parameter estimation using artificial neural networks","volume":"9","year":"2011","journal-title":"J. Appl. Res. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3335","DOI":"10.1016\/j.neucom.2008.01.030","article-title":"Long-term time series prediction with the NARX network: An empirical evaluation","volume":"71","author":"Barreto","year":"2008","journal-title":"Neurocomputing"},{"key":"ref_13","doi-asserted-by":"crossref","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":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, X., Yu, J., Xu, L., and Zhang, G. (2017, January 14\u201318). Time Series Classification with Deep Neural Networks Based on Hurst Exponent Analysis. Proceedings of the ICONIP 2017: Neural Information Processing, Guangzhou, China.","DOI":"10.1007\/978-3-319-70087-8_21"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"590","DOI":"10.3390\/econometrics3030590","article-title":"A Kolmogorov-Smirnov Based Test for Comparing the Predictive Accuracy of Two Sets of Forecasts","volume":"3","author":"Hassani","year":"2015","journal-title":"Econometrics"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1061\/TACEAT.0006518","article-title":"Long-term storage capacity of reservoirs","volume":"116","author":"Hurst","year":"1951","journal-title":"Trans. Am. Soc. Civ. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1137\/1010093","article-title":"Fractional Brownian motions, fractional noises and applications","volume":"10","author":"Mandelbrot","year":"1968","journal-title":"SIAM Rev."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1685","DOI":"10.1103\/PhysRevE.49.1685","article-title":"Mosaic organization of DNA nucleotides","volume":"49","author":"Peng","year":"1994","journal-title":"Phys. Rev. E"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1111\/j.1467-9892.1983.tb00371.x","article-title":"The estimation and application of long memory time series models","volume":"4","author":"Geweke","year":"1983","journal-title":"J. Time Ser. Anal."},{"key":"ref_20","unstructured":"Whittle, P. (1951). Hypothesis Testing in Time Series Analysis, Almqvist & Wiksells."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1109\/18.761330","article-title":"A wavelet-based joint estimator of the parameters of long-range dependence","volume":"45","author":"Veitch","year":"1999","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1142\/S0218348X95000692","article-title":"Estimators for long-range dependence: An empirical study","volume":"3","author":"Taqqu","year":"1995","journal-title":"Fractals"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1002\/(SICI)1099-131X(199711)16:6<395::AID-FOR660>3.0.CO;2-P","article-title":"Estimation and forecasting of long-memory processes with missing values","volume":"16","author":"Palma","year":"1997","journal-title":"J. Forecast."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1093\/biomet\/68.1.165","article-title":"Fractional differencing","volume":"68","author":"Hosking","year":"1981","journal-title":"Biometrika"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1214\/aos\/1176349936","article-title":"Large-sample properties of parameter estimates for strongly dependent stationary Gaussian time series","volume":"14","author":"Fox","year":"1986","journal-title":"Ann. Stat."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/BF02551274","article-title":"Approximation by superpositions of a sigmoidal function","volume":"2","author":"Cybenko","year":"1989","journal-title":"Math. Control. Signals Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Netw."},{"key":"ref_29","unstructured":"Salehinejad, H., Sankar, S., Barfett, J., Colak, E., and Valaee, S. (2017). Recent advances in recurrent neural networks. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1142\/S0129065707001111","article-title":"Recurrent neural networks are universal approximators","volume":"17","author":"Zimmermann","year":"2007","journal-title":"Int. J. Neural Syst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Bengio","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_33","unstructured":"Hochreiter, S., Bengio, Y., Frasconi, P., and Schmidhuber, J. (2001). Gradient Flow in Recurrent Nets: The Difficulty of Learning Long-Term Dependencies, IEEE Press."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Netw."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv.","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Chen, L. (2021). Deep Learning and Practice with MindSpore, Springer Nature.","DOI":"10.1007\/978-981-16-2233-5"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2309","DOI":"10.1007\/s00180-013-0408-7","article-title":"Statistical analysis of autoregressive fractionally integrated moving average models in R","volume":"28","author":"Palma","year":"2013","journal-title":"Comput. Stat."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2958","DOI":"10.1214\/10-AOS812","article-title":"An efficient estimator for locally stationary Gaussian long-memory processes","volume":"38","author":"Palma","year":"2010","journal-title":"Ann. Stat."},{"key":"ref_39","unstructured":"Singleton, R. (1972). Mixed Radix Fast Fourier Transform, Stanford Research Inst.. Technical Report."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1007\/BF02590998","article-title":"Estimation and information in stationary time series","volume":"2","author":"Whittle","year":"1953","journal-title":"Ark. Mat."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/S0167-9473(97)00045-5","article-title":"A comparison of techniques of estimation in long-memory processes","volume":"27","author":"Bisaglia","year":"1998","journal-title":"Comput. Stat. Data Anal."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Dahlhaus, R. (1989). Efficient parameter estimation for self-similar processes. Ann. Stat., 1749\u20131766.","DOI":"10.1214\/aos\/1176347393"},{"key":"ref_43","first-page":"133","article-title":"Statistical analysis of locally stationary processes","volume":"4","author":"Ferreira","year":"2013","journal-title":"Chil. J. Stat."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Beran, J., Feng, Y., Ghosh, S., and Kulik, R. (2013). Long-Memory Processes, Springer.","DOI":"10.1007\/978-3-642-35512-7"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Armstrong, J.S. (2001). Evaluating Forecasting Methods. Principles of Forecasting, Springer.","DOI":"10.1007\/978-0-306-47630-3_20"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/5\/4\/68\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:04:13Z","timestamp":1760130253000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/5\/4\/68"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,2]]},"references-count":45,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["make5040068"],"URL":"https:\/\/doi.org\/10.3390\/make5040068","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,2]]}}}