{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:35:27Z","timestamp":1777984527488,"version":"3.51.4"},"reference-count":59,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T00:00:00Z","timestamp":1658707200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Accurate forecasts of containerised freight volumes are unquestionably important for port terminal operators to organise port operations and develop business plans. They are also relevant for port authorities, regulators, and governmental agencies dealing with transportation. In a time when deep learning is in the limelight, owing to a consistent strip of success stories, it is natural to apply it to the tasks of forecasting container throughput. Given the number of options, practitioners can benefit from the lessons learned in applying deep learning models to the problem. Coherently, in this work, we devise a number of multivariate predictive models based on deep learning, analysing and assessing their performance to identify the architecture and set of hyperparameters that prove to be better suited to the task, also comparing the quality of the forecasts with seasonal autoregressive integrated moving average models. Furthermore, an innovative representation of seasonality is given by means of an embedding layer that produces a mapping in a latent space, with the parameters of such mapping being tuned using the quality of the predictions. Finally, we present some managerial implications, also putting into evidence the research limitations and future opportunities.<\/jats:p>","DOI":"10.3390\/fi14080221","type":"journal-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T21:20:59Z","timestamp":1658784059000},"page":"221","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Deep Learning Forecasting for Supporting Terminal Operators in Port Business Development"],"prefix":"10.3390","volume":"14","author":[{"given":"Marco","family":"Ferretti","sequence":"first","affiliation":[{"name":"Department of Management and Quantitative Studies, Parthenope University, 80132 Napoli, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ugo","family":"Fiore","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Salerno, 84040 Fisciano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesca","family":"Perla","sequence":"additional","affiliation":[{"name":"Department of Management and Quantitative Studies, Parthenope University, 80132 Napoli, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9579-5931","authenticated-orcid":false,"given":"Marcello","family":"Risitano","sequence":"additional","affiliation":[{"name":"Department of Management and Quantitative Studies, Parthenope University, 80132 Napoli, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5725-5061","authenticated-orcid":false,"given":"Salvatore","family":"Scognamiglio","sequence":"additional","affiliation":[{"name":"Department of Management and Quantitative Studies, Parthenope University, 80132 Napoli, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,7,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1016\/j.tre.2008.11.004","article-title":"Effect of block width and storage yard layout on marine container terminal performance","volume":"45","author":"Petering","year":"2009","journal-title":"Transp. Res. Part E Logist. Transp. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/j.tre.2004.05.002","article-title":"Determinants of the demand for maritime imports and exports","volume":"41","author":"Castro","year":"2005","journal-title":"Transp. Res. Part E Logist. Transp. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.tra.2005.07.003","article-title":"The technical efficiency of container ports: Comparing data envelopment analysis and stochastic frontier analysis","volume":"40","author":"Cullinane","year":"2006","journal-title":"Transp. Res. Part A Policy Pract."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1080\/01441647.2016.1231232","article-title":"The drivers of port competitiveness: A critical review","volume":"37","author":"Parola","year":"2017","journal-title":"Transp. Rev."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.jtrangeo.2013.09.010","article-title":"Analysis of factors underlying foreign entry strategies of terminal operators in container ports","volume":"33","author":"Parola","year":"2013","journal-title":"J. Transp. Geogr."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1057\/mel.2014.18","article-title":"Corporate strategies and profitability of maritime logistics firms","volume":"17","author":"Parola","year":"2015","journal-title":"Marit. Econ. Logist."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1057\/s41278-018-00116-0","article-title":"Gigantism in container shipping, ports and global logistics: A time-lapse into the future","volume":"21","author":"Haralambides","year":"2019","journal-title":"Marit. Econ. Logist."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Notteboom, T., Pallis, A., and Rodrigue, J.P. (2020). Port Economics. Management and Policy, Routledge.","DOI":"10.4324\/9780429318184"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1080\/0144164042000244608","article-title":"Determining container terminal capacity on the basis of an adopted yard handling system","volume":"25","author":"Chu","year":"2005","journal-title":"Transp. Rev."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1057\/s41278-019-00131-9","article-title":"Container terminal layout design: Transition and future","volume":"22","author":"Gharehgozli","year":"2019","journal-title":"Marit. Econ. Logist."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.tra.2005.03.001","article-title":"Competition dynamics between container ports in East Asia","volume":"40","author":"Yap","year":"2006","journal-title":"Transp. Res. Part A Policy Pract."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1057\/mel.2009.4","article-title":"The demand for import services at US container ports","volume":"11","author":"Anderson","year":"2009","journal-title":"Marit. Econ. Logist."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.1016\/j.jtrangeo.2011.05.005","article-title":"A strategic network choice model for global container flows: Specification, estimation and application","volume":"19","author":"Tavasszy","year":"2011","journal-title":"J. Transp. Geogr."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1080\/03088839.2019.1620359","article-title":"Next generation mega container ports: Implications of traffic composition on sea space demand","volume":"46","author":"Yap","year":"2019","journal-title":"Marit. Policy Manag."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1002\/for.818","article-title":"Forecasting Hong Kong\u2019s container throughput: An error-correction model","volume":"21","author":"Fung","year":"2002","journal-title":"J. Forecast."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1080\/03088831003700645","article-title":"A review of port authority functions: Towards a renaissance?","volume":"37","author":"Verhoeven","year":"2010","journal-title":"Marit. Policy Manag."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1016\/j.jtrangeo.2010.03.004","article-title":"Understanding hinterland service integration by shipping lines and terminal operators: A theoretical and empirical analysis","volume":"18","author":"Franc","year":"2010","journal-title":"J. Transp. Geogr."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"920","DOI":"10.1080\/03088839.2019.1594426","article-title":"Vertical integration and its implications to port expansion","volume":"46","author":"Zhu","year":"2019","journal-title":"Marit. Policy Manag."},{"key":"ref_19","first-page":"5","article-title":"Planning and concession management under port co-operation schemes: A multiple case study of Italian port mergers","volume":"26","author":"Ferretti","year":"2018","journal-title":"Res. Transp. Bus. Manag."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.tra.2018.03.012","article-title":"Marketing strategies of Port Authorities: A multi-dimensional theorisation","volume":"111","author":"Parola","year":"2018","journal-title":"Transp. Res. Part A Policy Pract."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.tranpol.2018.11.011","article-title":"Port marketing from a multidisciplinary perspective: A systematic literature review and lexicometric analysis","volume":"84","author":"Hofmann","year":"2019","journal-title":"Transp. Policy"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"103896","DOI":"10.1016\/j.marpol.2020.103896","article-title":"Key factors of container port competitiveness: A global shipping lines perspective","volume":"117","author":"Kaliszewski","year":"2020","journal-title":"Mar. Policy"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"5674","DOI":"10.1109\/TII.2019.2927749","article-title":"Do Digital and Communication Technologies Improve Smart Ports? A Fuzzy DEA Approach","volume":"15","author":"Castellano","year":"2019","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1080\/15568318.2019.1610919","article-title":"A framework for building a smart port and smart port index","volume":"14","author":"Molavi","year":"2020","journal-title":"Int. J. Sustain. Transp."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1354","DOI":"10.1080\/09537287.2017.1375146","article-title":"Strategic monitoring of port authorities activities: Proposal of a multi-dimensional digital dashboard","volume":"28","author":"Ferretti","year":"2017","journal-title":"Prod. Plan. Control"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.ejor.2020.08.001","article-title":"Forecasting and planning during a pandemic: COVID-19 growth rates, supply chain disruptions, and governmental decisions","volume":"290","author":"Nikolopoulos","year":"2021","journal-title":"Eur. J. Oper. Res."},{"key":"ref_27","unstructured":"Box, G.E., Jenkins, G.M., Reinsel, G.C., and Ljung, G.M. (2015). Time Series Analysis: Forecasting and Control, John Wiley & Sons."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1080\/13675567.2018.1525342","article-title":"A comparison of time series methods for forecasting container throughput","volume":"22","author":"Chan","year":"2019","journal-title":"Int. J. Logist. Res. Appl."},{"key":"ref_29","first-page":"21","article-title":"The comparison of the seasonal forecasting models: A study on the prediction of imported container volume for international container ports in Taiwan","volume":"25","author":"Peng","year":"2006","journal-title":"Marit. Q."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1016\/j.mcm.2009.05.027","article-title":"A comparison of univariate methods for forecasting container throughput volumes","volume":"50","author":"Peng","year":"2009","journal-title":"Math. Comput. Model."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2809","DOI":"10.1080\/00036840802260932","article-title":"Forecasting container transshipment in Germany","volume":"41","author":"Schulze","year":"2009","journal-title":"Appl. Econ."},{"key":"ref_32","unstructured":"Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning, MIT Press Cambridge."},{"key":"ref_33","unstructured":"Vapnik, V. (2013). The Nature of Statistical Learning Theory, Springer Science & Business Media."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1007\/s10696-018-9324-z","article-title":"Integrated method for forecasting container slot booking in intercontinental liner shipping service","volume":"31","author":"Wang","year":"2019","journal-title":"Flex. Serv. Manuf. J."},{"key":"ref_35","first-page":"51","article-title":"Forecasting Port Cargo Throughput Based on Grey Wave Forecasting Model with Generalized Contour Lines","volume":"29","author":"Chen","year":"2017","journal-title":"J. Grey Syst."},{"key":"ref_36","first-page":"100453","article-title":"Machine learning for international freight transportation management: A comprehensive review","volume":"34","author":"Barua","year":"2020","journal-title":"Res. Transp. Bus. Manag."},{"key":"ref_37","first-page":"1","article-title":"A study on transit containers forecast in Kaohsiung port: Applying artificial neural networks to evaluating input variables","volume":"11","author":"Wei","year":"1999","journal-title":"J. Chin. Inst. Transp."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1016\/S2092-5212(11)80022-2","article-title":"A comparison of traditional and neural networks forecasting techniques for container throughput at Bangkok port","volume":"27","author":"Gosasang","year":"2011","journal-title":"Asian J. Shipp. Logist."},{"key":"ref_39","first-page":"965","article-title":"Container flow forecasting through neural networks based on metaheuristics","volume":"21","author":"Milosavljevic","year":"2021","journal-title":"Oper. Res."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2232","DOI":"10.1016\/j.asoc.2013.02.002","article-title":"Hybrid approaches based on LSSVR model for container throughput forecasting: A comparative study","volume":"13","author":"Xie","year":"2013","journal-title":"Appl. Soft Comput."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"105683","DOI":"10.1016\/j.asoc.2019.105683","article-title":"A generative neural network model for the quality prediction of work in progress products","volume":"85","author":"Wang","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Zhou, X., Dong, P., Xing, J., and Sun, P. (2019). Learning dynamic factors to improve the accuracy of bus arrival time prediction via a recurrent neural network. Future Internet, 11.","DOI":"10.3390\/fi11120247"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"104853","DOI":"10.1016\/j.knosys.2019.07.024","article-title":"Container throughput forecasting using a novel hybrid learning method with error correction strategy","volume":"182","author":"Du","year":"2019","journal-title":"Knowl.-Based Syst."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1108\/IMDS-07-2019-0370","article-title":"Forecasting container throughput with long short-term memory networks","volume":"120","author":"Shankar","year":"2019","journal-title":"Ind. Manag. Data Syst."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn. Sci."},{"key":"ref_46","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_47","doi-asserted-by":"crossref","first-page":"2451","DOI":"10.1162\/089976600300015015","article-title":"Learning to Forget: Continual Prediction with LSTM","volume":"12","author":"Gers","year":"2000","journal-title":"Neural Comput."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Graziani, S., and Xibilia, M.G. (2020). Innovative Topologies and Algorithms for Neural Networks. Future Internet, 12.","DOI":"10.3390\/fi12070117"},{"key":"ref_49","unstructured":"Bengio, Y., Ducharme, R., and Vincent, P. (2022, June 19). A Neural Probabilistic Language Model. Available online: https:\/\/proceedings.neurips.cc\/paper\/2000\/file\/728f206c2a01bf572b5940d7d9a8fa4c-Paper.pdf."},{"key":"ref_50","unstructured":"Guo, C., and Berkhahn, F. (2016). Entity embeddings of categorical variables. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/s10479-019-03144-y","article-title":"Neural networks in financial trading","volume":"297","author":"Sermpinis","year":"2019","journal-title":"Ann. Oper. Res."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Kumar, A., Singh, J.P., Dwivedi, Y.K., and Rana, N.P. (2020). A deep multi-modal neural network for informative Twitter content classification during emergencies. Ann. Oper. Res., 1\u201332.","DOI":"10.1007\/s10479-020-03514-x"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","article-title":"LSTM: A search space odyssey","volume":"28","author":"Greff","year":"2016","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_54","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_55","unstructured":"LeCun, Y., Boser, B.E., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W.E., and Jackel, L.D. (1990, January 26\u201329). Handwritten digit recognition with a back-propagation network. Proceedings of the Advances in Neural Information Processing Systems, Denver, CO, USA."},{"key":"ref_56","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_57","unstructured":"Hyndman, R.J., and Khandakar, Y. (2007). Automatic Time Series for Forecasting: The Forecast Package for R, Monash University, Department of Econometrics and Business Statistics. Number 6\/07."},{"key":"ref_58","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., Friedman, J.H., and Friedman, J.H. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer.","DOI":"10.1007\/978-0-387-84858-7"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/14\/8\/221\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:56:06Z","timestamp":1760140566000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/14\/8\/221"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,25]]},"references-count":59,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["fi14080221"],"URL":"https:\/\/doi.org\/10.3390\/fi14080221","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,25]]}}}