{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T16:26:13Z","timestamp":1768321573733,"version":"3.49.0"},"reference-count":63,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T00:00:00Z","timestamp":1681257600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>We present a machine learning approach for applying (multiple) temporal aggregation in time series forecasting settings. The method utilizes a classification model that can be used to either select the most appropriate temporal aggregation level for producing forecasts or to derive weights to properly combine the forecasts generated at various levels. The classifier consists a meta-learner that correlates key time series features with forecasting accuracy, thus enabling a dynamic, data-driven selection or combination. Our experiments, conducted in two large data sets of slow- and fast-moving series, indicate that the proposed meta-learner can outperform standard forecasting approaches.<\/jats:p>","DOI":"10.3390\/a16040206","type":"journal-article","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T01:35:00Z","timestamp":1681349700000},"page":"206","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Conditional Temporal Aggregation for Time Series Forecasting Using Feature-Based Meta-Learning"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5419-1725","authenticated-orcid":false,"given":"Anastasios","family":"Kaltsounis","sequence":"first","affiliation":[{"name":"Forecasting and Strategy Unit, School of Electrical & Computer Engineering, National Technical University of Athens, 157 80 Athens, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1854-1206","authenticated-orcid":false,"given":"Evangelos","family":"Spiliotis","sequence":"additional","affiliation":[{"name":"Forecasting and Strategy Unit, School of Electrical & Computer Engineering, National Technical University of Athens, 157 80 Athens, Greece"}]},{"given":"Vassilios","family":"Assimakopoulos","sequence":"additional","affiliation":[{"name":"Forecasting and Strategy Unit, School of Electrical & Computer Engineering, National Technical University of Athens, 157 80 Athens, Greece"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.1016\/j.jbusres.2015.03.028","article-title":"Simple versus complex selection rules for forecasting many time series","volume":"68","author":"Fildes","year":"2015","journal-title":"J. Bus. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1016\/j.ejor.2018.01.045","article-title":"Exploring the sources of uncertainty: Why does bagging for time series forecasting work?","volume":"268","author":"Petropoulos","year":"2018","journal-title":"Eur. J. Oper. Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1016\/j.ijforecast.2015.12.005","article-title":"The forecast combination puzzle: A simple theoretical explanation","volume":"32","author":"Claeskens","year":"2016","journal-title":"Int. J. Forecast."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.ijforecast.2019.04.014","article-title":"The M4 Competition: 100,000 time series and 61 forecasting methods","volume":"36","author":"Makridakis","year":"2020","journal-title":"Int. J. Forecast."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"478","DOI":"10.3390\/forecast3030029","article-title":"The Wisdom of the Data: Getting the Most Out of Univariate Time Series Forecasting","volume":"3","author":"Petropoulos","year":"2021","journal-title":"Forecasting"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1016\/j.ijforecast.2021.11.001","article-title":"Forecasting: Theory and practice","volume":"38","author":"Petropoulos","year":"2022","journal-title":"Int. J. Forecast."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/j.ijforecast.2020.06.004","article-title":"Forecast reconciliation: A geometric view with new insights on bias correction","volume":"37","author":"Panagiotelis","year":"2021","journal-title":"Int. J. Forecast."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1057\/jors.2010.32","article-title":"An aggregate\u2013disaggregate intermittent demand approach (ADIDA) to forecasting: An empirical proposition and analysis","volume":"62","author":"Nikolopoulos","year":"2011","journal-title":"J. Oper. Res. Soc."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1057\/jors.2014.62","article-title":"Forecast combinations for intermittent demand","volume":"66","author":"Petropoulos","year":"2015","journal-title":"J. Oper. Res. Soc."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1016\/j.ijpe.2016.04.017","article-title":"Another look at estimators for intermittent demand","volume":"181","author":"Petropoulos","year":"2016","journal-title":"Int. J. Prod. Econ."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.ejor.2020.05.046","article-title":"Elucidate structure in intermittent demand series","volume":"288","author":"Kourentzes","year":"2021","journal-title":"Eur. J. Oper. Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.ijforecast.2013.09.006","article-title":"Improving forecasting by estimating time series structural components across multiple frequencies","volume":"30","author":"Kourentzes","year":"2014","journal-title":"Int. J. Forecast."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.ejor.2017.02.046","article-title":"Forecasting with temporal hierarchies","volume":"262","author":"Athanasopoulos","year":"2017","journal-title":"Eur. J. Oper. Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/j.ijforecast.2004.10.001","article-title":"The accuracy of intermittent demand estimates","volume":"21","author":"Syntetos","year":"2005","journal-title":"Int. J. Forecast."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.ijpe.2016.04.003","article-title":"On the performance of overlapping and non-overlapping temporal demand aggregation approaches","volume":"181","author":"Boylan","year":"2016","journal-title":"Int. J. Prod. Econ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"114339","DOI":"10.1016\/j.apenergy.2019.114339","article-title":"Cross-temporal aggregation: Improving the forecast accuracy of hierarchical electricity consumption","volume":"261","author":"Spiliotis","year":"2020","journal-title":"Appl. Energy"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.ejor.2021.01.017","article-title":"Understanding forecast reconciliation","volume":"294","author":"Hollyman","year":"2021","journal-title":"Eur. J. Oper. Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"870","DOI":"10.1016\/j.ijforecast.2010.05.019","article-title":"Combination of long term and short term forecasts, with application to tourism demand forecasting","volume":"27","author":"Andrawis","year":"2011","journal-title":"Int. J. Forecast."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jbusres.2017.04.016","article-title":"Demand forecasting by temporal aggregation: Using optimal or multiple aggregation levels?","volume":"78","author":"Kourentzes","year":"2017","journal-title":"J. Bus. Res."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Spiliotis, E., Petropoulos, F., and Assimakopoulos, V. (2019). Improving the forecasting performance of temporal hierarchies. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0223422"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"804","DOI":"10.1080\/01621459.2018.1448825","article-title":"Optimal Forecast Reconciliation for Hierarchical and Grouped Time Series Through Trace Minimization","volume":"114","author":"Wickramasuriya","year":"2019","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1016\/j.ejor.2019.05.020","article-title":"Probabilistic forecast reconciliation with applications to wind power and electric load","volume":"279","author":"Jeon","year":"2019","journal-title":"Eur. J. Oper. Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"107756","DOI":"10.1016\/j.asoc.2021.107756","article-title":"Hierarchical forecast reconciliation with machine learning","volume":"112","author":"Spiliotis","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1500","DOI":"10.1016\/j.ijforecast.2021.07.006","article-title":"Exploring the representativeness of the M5 competition data","volume":"38","author":"Theodorou","year":"2022","journal-title":"Int. J. Forecast."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.ejor.2014.02.036","article-title":"\u2018Horses for Courses\u2019 in demand forecasting","volume":"237","author":"Petropoulos","year":"2014","journal-title":"Eur. J. Oper. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"920","DOI":"10.1016\/j.ijforecast.2021.07.002","article-title":"FFORMPP: Feature-based forecast model performance prediction","volume":"38","author":"Talagala","year":"2021","journal-title":"Int. J. Forecast."},{"key":"ref_27","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Advances in Neural Information Processing Systems 30, Curran Associates, Inc."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1007\/s10994-021-06126-z","article-title":"Model selection in reconciling hierarchical time series","volume":"111","author":"Abolghasemi","year":"2022","journal-title":"Mach. Learn."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1346","DOI":"10.1016\/j.ijforecast.2021.11.013","article-title":"M5 accuracy competition: Results, findings, and conclusions","volume":"38","author":"Makridakis","year":"2022","journal-title":"Int. J. Forecast."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.ijforecast.2019.02.011","article-title":"FFORMA: Feature-based forecast model averaging","volume":"36","author":"Athanasopoulos","year":"2020","journal-title":"Int. J. Forecast."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1080\/16258312.2011.11517277","article-title":"Improving the Performance of Popular Supply Chain Forecasting Techniques","volume":"12","author":"Spithourakis","year":"2011","journal-title":"Supply Chain Forum Int. J."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1080\/01621459.1972.10481264","article-title":"The Effect of Aggregation on Prediction in the Autoregressive Model","volume":"67","author":"Amemiya","year":"1972","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1080\/07350015.1995.10524618","article-title":"Temporal Aggregation and Economic Time Series","volume":"13","author":"Rossana","year":"1995","journal-title":"J. Bus. Econ. Stat."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1111\/j.1467-9892.1986.tb00495.x","article-title":"Temporal aggregation in the ARIMA process","volume":"7","author":"Stram","year":"2008","journal-title":"J. Time Ser. Anal."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"822","DOI":"10.1016\/j.ijforecast.2010.04.009","article-title":"The tourism forecasting competition","volume":"27","author":"Athanasopoulos","year":"2011","journal-title":"Int. J. Forecast."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1057\/jors.1969.103","article-title":"The Combination of Forecasts","volume":"20","author":"Bates","year":"1969","journal-title":"J. Oper. Res. Soc."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1016\/0169-2070(89)90012-5","article-title":"Combining forecasts: A review and annotated bibliography","volume":"5","author":"Clemen","year":"1989","journal-title":"Int. J. Forecast."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1002\/for.942","article-title":"Combination of forecasts using self-organizing algorithms","volume":"24","author":"He","year":"2005","journal-title":"J. Forecast."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/j.ijforecast.2008.06.003","article-title":"Exponentially weighted information criteria for selecting among forecasting models","volume":"24","author":"Taylor","year":"2008","journal-title":"Int. J. Forecast."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/j.ijforecast.2010.04.006","article-title":"Combining exponential smoothing forecasts using Akaike weights","volume":"27","author":"Kolassa","year":"2011","journal-title":"Int. J. Forecast."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.ijforecast.2019.01.006","article-title":"A simple combination of univariate models","volume":"36","author":"Petropoulos","year":"2020","journal-title":"Int. J. Forecast."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"4235","DOI":"10.1016\/j.eswa.2013.12.011","article-title":"Neural network ensemble operators for time series forecasting","volume":"41","author":"Kourentzes","year":"2014","journal-title":"Expert Syst. Appl."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1016\/S0169-2070(00)00065-0","article-title":"Out-of-sample tests of forecasting accuracy: An analysis and review","volume":"16","author":"Tashman","year":"2000","journal-title":"Int. J. Forecast."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1016\/S0169-2070(97)00031-9","article-title":"Model selection in univariate time series forecasting using discriminant analysis","volume":"13","author":"Shah","year":"1997","journal-title":"Int. J. Forecast."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1002\/1099-131X(200011)19:6<515::AID-FOR754>3.0.CO;2-7","article-title":"Evidence for the selection of forecasting methods","volume":"19","author":"Meade","year":"2000","journal-title":"J. Forecast."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1394","DOI":"10.1287\/mnsc.38.10.1394","article-title":"Rule-Based Forecasting: Development and Validation of an Expert Systems Approach to Combining Time Series Extrapolations","volume":"38","author":"Collopy","year":"1992","journal-title":"Manag. Sci."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1016\/S0169-2070(00)00086-8","article-title":"The Forecast Pro methodology","volume":"16","author":"Goodrich","year":"2000","journal-title":"Int. J. Forecast."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1016\/S0169-2070(00)00074-1","article-title":"An application of rule-based forecasting to a situation lacking domain knowledge","volume":"16","author":"Adya","year":"2000","journal-title":"Int. J. Forecast."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/S0169-2070(01)00079-6","article-title":"Automatic identification of time series features for rule-based forecasting","volume":"17","author":"Adya","year":"2001","journal-title":"Int. J. Forecast."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/j.ijforecast.2016.09.004","article-title":"Visualising forecasting algorithm performance using time series instance spaces","volume":"33","author":"Kang","year":"2017","journal-title":"Int. J. Forecast."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.ijforecast.2018.12.007","article-title":"Are forecasting competitions data representative of the reality?","volume":"36","author":"Spiliotis","year":"2020","journal-title":"Int. J. Forecast."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.ijforecast.2019.02.017","article-title":"Why the \u201cbest\u201d point forecast depends on the error or accuracy measure","volume":"36","author":"Kolassa","year":"2020","journal-title":"Int. J. Forecast."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Hyndman, R., Kang, Y., Montero-Manso, P., Talagala, T., Wang, E., Yang, Y., and O\u2019Hara-Wild, M. (2023, April 10). tsfeatures: Time Series Feature Extraction; R Package Version 1.0.2; 2020. Available online: https:\/\/cran.r-project.org\/web\/packages\/tsfeatures\/vignettes\/tsfeatures.html.","DOI":"10.32614\/CRAN.package.tsfeatures"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"2006","DOI":"10.1016\/j.neucom.2009.09.020","article-title":"Meta-learning for time series forecasting and forecast combination","volume":"73","author":"Lemke","year":"2010","journal-title":"Neurocomputing"},{"key":"ref_55","first-page":"12","article-title":"A Hybrid Neural Network and Traditional Approach for Forecasting Lumpy Demand","volume":"2","author":"Rahimzadeh","year":"2009","journal-title":"World Acad. Sci. Eng. Technol."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1057\/palgrave.jors.2601841","article-title":"On the categorization of demand patterns","volume":"56","author":"Syntetos","year":"2005","journal-title":"J. Oper. Res. Soc."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1016\/j.ijforecast.2006.03.001","article-title":"Another look at measures of forecast accuracy","volume":"22","author":"Hyndman","year":"2006","journal-title":"Int. J. Forecast."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1016\/j.ijforecast.2015.12.004","article-title":"Evaluating predictive count data distributions in retail sales forecasting","volume":"32","author":"Kolassa","year":"2016","journal-title":"Int. J. Forecast."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1080\/00031305.1990.10475690","article-title":"A Simple Noncalculus Proof That the Median Minimizes the Sum of the Absolute Deviations","volume":"44","author":"Schwertman","year":"1990","journal-title":"Am. Stat."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1016\/S0169-2070(01)00110-8","article-title":"A state space framework for automatic forecasting using exponential smoothing methods","volume":"18","author":"Hyndman","year":"2002","journal-title":"Int. J. Forecast."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v027.i03","article-title":"Automatic Time Series Forecasting: The forecast Package for R","volume":"27","author":"Hyndman","year":"2008","journal-title":"J. Stat. Softw."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1016\/S0169-2070(00)00066-2","article-title":"The theta model: A decomposition approach to forecasting","volume":"16","author":"Assimakopoulos","year":"2000","journal-title":"Int. J. Forecast."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1016\/j.ijforecast.2004.10.003","article-title":"The M3 competition: Statistical tests of the results","volume":"21","author":"Koning","year":"2005","journal-title":"Int. J. Forecast."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/4\/206\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:14:44Z","timestamp":1760123684000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/4\/206"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,12]]},"references-count":63,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["a16040206"],"URL":"https:\/\/doi.org\/10.3390\/a16040206","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,12]]}}}