{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T13:48:30Z","timestamp":1775483310495,"version":"3.50.1"},"reference-count":56,"publisher":"Emerald","issue":"3","license":[{"start":{"date-parts":[[2019,12,4]],"date-time":"2019-12-04T00:00:00Z","timestamp":1575417600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IMDS"],"published-print":{"date-parts":[[2019,12,4]]},"abstract":"<jats:sec><jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title><jats:p>Better forecasting always leads to better management and planning of the operations. The container throughput data are complex and often have multiple seasonality. This makes it difficult to forecast accurately. The purpose of this paper is to forecast container throughput using deep learning methods and benchmark its performance over other traditional time-series methods.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title><jats:p>In this study, long short-term memory (LSTM) networks are implemented to forecast container throughput. The container throughput data of the Port of Singapore are used for empirical analysis. The forecasting performance of the LSTM model is compared with seven different time-series forecasting methods, namely, autoregressive integrated moving average (ARIMA), simple exponential smoothing, Holt\u2013Winter\u2019s, error-trend-seasonality, trigonometric regressors (TBATS), neural network (NN) and ARIMA + NN. The relative error matrix is used to analyze the performance of the different models with respect to bias, accuracy and uncertainty.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Findings<\/jats:title><jats:p>The results showed that LSTM outperformed all other benchmark methods. From a statistical perspective, the Diebold\u2013Mariano test is also conducted to further substantiate better forecasting performance of LSTM over other counterpart methods.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title><jats:p>The proposed study is a contribution to the literature on the container throughput forecasting and adds value to the supply chain theory of forecasting. Second, this study explained the architecture of the deep-learning-based LSTM method and discussed in detail the steps to implement it.<\/jats:p><\/jats:sec>","DOI":"10.1108\/imds-07-2019-0370","type":"journal-article","created":{"date-parts":[[2020,1,8]],"date-time":"2020-01-08T08:04:56Z","timestamp":1578470696000},"page":"425-441","source":"Crossref","is-referenced-by-count":65,"title":["Forecasting container throughput with long short-term memory networks"],"prefix":"10.1108","volume":"120","author":[{"given":"Sonali","family":"Shankar","sequence":"first","affiliation":[]},{"given":"P. Vigneswara","family":"Ilavarasan","sequence":"additional","affiliation":[]},{"given":"Sushil","family":"Punia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3867-6845","authenticated-orcid":false,"given":"Surya Prakash","family":"Singh","sequence":"additional","affiliation":[]}],"member":"140","reference":[{"issue":"2","key":"key2020032509573683000_ref001","doi-asserted-by":"crossref","first-page":"409","DOI":"10.5267\/j.ijiec.2011.01.001","article-title":"Design and analysis of experiments in ANFIS modeling for stock price prediction","volume":"2","year":"2011","journal-title":"International Journal of Industrial Engineering Computations"},{"key":"key2020032509573683000_ref002","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.chaos.2019.07.011","article-title":"Digital currency forecasting with chaotic meta-heuristic bio-inspired signal processing techniques","volume":"126","year":"2019","journal-title":"Chaos, Solitons & Fractals"},{"key":"key2020032509573683000_ref003","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1016\/j.eswa.2018.07.019","article-title":"ModAugNet: a new forecasting framework for stock market index value with an overfitting prevention LSTM module and a prediction LSTM module","volume":"113","year":"2018","journal-title":"Expert Systems with Applications"},{"key":"key2020032509573683000_ref004","doi-asserted-by":"crossref","first-page":"112896","DOI":"10.1016\/j.eswa.2019.112896","article-title":"Forecasting across time series databases using recurrent neural networks on groups of similar series: a clustering approach","volume":"140","year":"2020","journal-title":"Expert Systems with Applications"},{"issue":"2","key":"key2020032509573683000_ref005","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","year":"1994","journal-title":"IEEE Transactions on Neural Networks"},{"key":"key2020032509573683000_ref006","first-page":"2546","article-title":"Algorithms for hyper-parameter optimization","year":"2011"},{"issue":"3","key":"key2020032509573683000_ref007","doi-asserted-by":"crossref","first-page":"1357","DOI":"10.1016\/j.ejor.2005.02.012","article-title":"Neural network approach to forecasting of quasiperiodic financial time series","volume":"175","year":"2006","journal-title":"European Journal of Operational Research"},{"issue":"2","key":"key2020032509573683000_ref008","first-page":"103","article-title":"Short-term wind power forecasting using long-short term memory based recurrent neural network model and variable selection","volume":"8","year":"2019","journal-title":"International Journal of Smart Grid and Clean Energy"},{"key":"key2020032509573683000_ref009","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.physa.2018.11.061","article-title":"Financial time series forecasting model based on CEEMDAN and LSTM","volume":"519","year":"2019","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"key2020032509573683000_ref010","doi-asserted-by":"crossref","unstructured":"Chan, H.K., Xu, S. and Qi, X. (2018), \u201cA comparison of time series methods for forecasting container throughput\u201d, Vol. 22 No. 3, pp. 294-303, available at: https:\/\/doi.org\/10.1080\/13675567.2018.1525342","DOI":"10.1080\/13675567.2018.1525342"},{"issue":"3","key":"key2020032509573683000_ref011","doi-asserted-by":"crossref","first-page":"2054","DOI":"10.1016\/j.eswa.2009.06.054","article-title":"Forecasting container throughputs at ports using genetic programming","volume":"37","year":"2010","journal-title":"Expert Systems with Applications"},{"key":"key2020032509573683000_ref012","article-title":"Keras\u201d","year":"2015"},{"issue":"2","key":"key2020032509573683000_ref013","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/j.ijforecast.2003.10.004","article-title":"Forecasting economic and financial time-series with non-linear models","volume":"20","year":"2004","journal-title":"International Journal of Forecasting"},{"issue":"496","key":"key2020032509573683000_ref014","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1198\/jasa.2011.tm09771","article-title":"Forecasting time series with complex seasonal patterns using exponential smoothing","volume":"106","year":"2011","journal-title":"Journal of the American Statistical Association"},{"issue":"2","key":"key2020032509573683000_ref015","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/S2092-5212(11)80010-6","article-title":"Forecasting empty container volumes","volume":"27","year":"2011","journal-title":"The Asian Journal of Shipping and Logistics"},{"issue":"3","key":"key2020032509573683000_ref401","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1080\/07350015.1995.10524599","article-title":"Comparing predictive accuracy","volume":"13","year":"1995","journal-title":"Journal of Business & Economic Statistics"},{"issue":"7","key":"key2020032509573683000_ref016","first-page":"163","article-title":"Univariate throughput forecasting models on container terminal equipment planning","volume":"69","year":"2014","journal-title":"Jurnal Teknologi (Sciences and Engineering)"},{"key":"key2020032509573683000_ref017","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.tranpol.2019.01.013","article-title":"From a feeder port to a hub port: the evolution pathways, dynamics and perspectives of Ningbo-Zhoushan port (China)","volume":"76","year":"2019","journal-title":"Transport Policy"},{"issue":"2","key":"key2020032509573683000_ref018","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1016\/j.ejor.2017.11.054","article-title":"Deep learning with long short-term memory networks for financial market predictions","volume":"270","year":"2018","journal-title":"European Journal of Operational Research"},{"issue":"1","key":"key2020032509573683000_ref019","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1080\/03088830119563","article-title":"Competition between the ports of Hong Kong and Singapore: a structural vector error correction model to forecast the demand for container handling services","volume":"28","year":"2001","journal-title":"Maritime Policy and Management"},{"issue":"1","key":"key2020032509573683000_ref020","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","year":"2002","journal-title":"Journal of Forecasting"},{"key":"key2020032509573683000_ref021","first-page":"1050","article-title":"Dropout as a Bayesian approximation: representing model uncertainty in deep learning","year":"2016"},{"key":"key2020032509573683000_ref022","doi-asserted-by":"crossref","first-page":"157","DOI":"10.4028\/www.scientific.net\/JERA.28.157","article-title":"Application of several models for the forecasting of the container throughput of the Abidjan port in Ivory Coast","volume":"28","year":"2017","journal-title":"International Journal of Engineering Research in Africa"},{"key":"key2020032509573683000_ref023","doi-asserted-by":"crossref","first-page":"115838","DOI":"10.1016\/j.energy.2019.07.168","article-title":"Day-ahead power forecasting in a large-scale photovoltaic plant based on weather classification using LSTM","volume":"187","year":"2019","journal-title":"Energy"},{"issue":"4","key":"key2020032509573683000_ref024","first-page":"366","article-title":"Forecasting with model selection or model averaging: a case study for monthly container port throughput","volume":"12","year":"2016","journal-title":"Transportmetrica A: Transport Science"},{"issue":"8","key":"key2020032509573683000_ref025","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","year":"1997","journal-title":"Neural Computation"},{"issue":"6","key":"key2020032509573683000_ref026","first-page":"7","article-title":"Forecast: forecasting functions for time series and linear models","volume":"6","year":"2015","journal-title":"R Package Version"},{"issue":"6","key":"key2020032509573683000_ref027","doi-asserted-by":"crossref","first-page":"1242","DOI":"10.1108\/IMDS-11-2015-0463","article-title":"Thailand tourism forecasting based on a hybrid of discrete wavelet decomposition and NARX neural network","volume":"116","year":"2016","journal-title":"Industrial Management & Data Systems"},{"key":"key2020032509573683000_ref028","volume-title":"Grey Systems: Theory and Applications","year":"2010"},{"issue":"4","key":"key2020032509573683000_ref029","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1016\/S0169-2070(00)00057-1","article-title":"The M3-competition: results, conclusions and implications","volume":"16","year":"2000","journal-title":"International Journal of Forecasting"},{"issue":"2","key":"key2020032509573683000_ref030","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1002\/for.3980010202","article-title":"The accuracy of extrapolation (time series) methods: results of a forecasting competition","volume":"1","year":"1982","journal-title":"Journal of Forecasting"},{"key":"key2020032509573683000_ref031","doi-asserted-by":"crossref","unstructured":"Muzaffar, S. and Afshari, A. (2019), \u201cShort-term load forecasts using LSTM networks\u201d, in Li, H., Yang, H.-X., Chen, X. and Yan, J. (Eds), Energy Procedia, Vol. 158, Presented at the 10th International Conference on Applied Energy 2018, Elsevier, pp. 2922-2927.","DOI":"10.1016\/j.egypro.2019.01.952"},{"key":"key2020032509573683000_ref032","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/j.apm.2018.01.014","article-title":"A novel hybrid decomposition-ensemble model based on VMD and HGWO for container throughput forecasting","volume":"57","year":"2018","journal-title":"Applied Mathematical Modelling"},{"issue":"7-8","key":"key2020032509573683000_ref033","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","year":"2009","journal-title":"Mathematical and Computer Modelling"},{"key":"key2020032509573683000_ref034","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1016\/j.energy.2018.01.177","article-title":"Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM","volume":"148","year":"2018","journal-title":"Energy"},{"key":"key2020032509573683000_ref035","first-page":"127","article-title":"A combined approach to forecast container throughput demand: scenarios for the Hamburg-le Havre range of ports","volume":"117","year":"2018","journal-title":"Transportation Research Part A: Policy and Practice"},{"key":"key2020032509573683000_ref036","doi-asserted-by":"crossref","unstructured":"Salman, A.G., Heryadi, Y., Abdurahman, E. and Suparta, W. (2018), \u201cSingle layer & multi-layer long short-term memory (LSTM) model with intermediate variables for weather forecasting\u201d, Procedia Computer Science, Vol. 135, pp. 89-98.","DOI":"10.1016\/j.procs.2018.08.153"},{"issue":"22","key":"key2020032509573683000_ref037","doi-asserted-by":"crossref","first-page":"2809","DOI":"10.1080\/00036840802260932","article-title":"Forecasting container transshipment in Germany","volume":"41","year":"2009","journal-title":"Applied Economics"},{"issue":"7","key":"key2020032509573683000_ref038","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1108\/02635571211255032","article-title":"Future of transshipment in Singapore","volume":"112","year":"2012","journal-title":"Industrial Management & Data Systems"},{"issue":"12","key":"key2020032509573683000_ref039","article-title":"A deep neural network model for short-term load forecast based on long short-term memory network and convolutional neural network","volume":"11","year":"2018","journal-title":"Energies"},{"issue":"1","key":"key2020032509573683000_ref040","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/S0040-1625(00)00113-X","article-title":"Combining neural network model with seasonal time series ARIMA model","volume":"69","year":"2002","journal-title":"Technological Forecasting and Social Change"},{"key":"key2020032509573683000_ref041","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.jtrangeo.2016.03.005","article-title":"Modeling of container throughput in Northern Adriatic Ports over the period 1990-2013","volume":"52","year":"2016","journal-title":"Journal of Transport Geography"},{"issue":"1","key":"key2020032509573683000_ref042","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1057\/palgrave.mel.9100058","article-title":"A model on container port competition: an application for the West European container Hub-Ports","volume":"5","year":"2003","journal-title":"Maritime Economics and Logistics"},{"key":"key2020032509573683000_ref043","first-page":"116225","article-title":"Photovoltaic power forecasting based LSTM-convolutional network","year":"2019","journal-title":"Energy"},{"key":"key2020032509573683000_ref044","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1016\/j.energy.2019.04.115","article-title":"Integrating linear and nonlinear forecasting techniques based on grey theory and artificial intelligence to forecast shale gas monthly production in Pennsylvania and Texas of the United States","volume":"178","year":"2019","journal-title":"Energy"},{"issue":"2","key":"key2020032509573683000_ref045","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1016\/j.ejor.2010.05.022","article-title":"Adaptive neural network model for time-series forecasting","volume":"207","year":"2010","journal-title":"European Journal of Operational Research"},{"key":"key2020032509573683000_ref046","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.physa.2018.09.120","article-title":"Improved EEMD-based crude oil price forecasting using LSTM networks","volume":"516","year":"2019","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"issue":"1","key":"key2020032509573683000_ref047","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s11424-014-3296-1","article-title":"A transfer forecasting model for container throughput guided by discrete PSO","volume":"27","year":"2014","journal-title":"Journal of Systems Science and Complexity"},{"issue":"2","key":"key2020032509573683000_ref048","doi-asserted-by":"crossref","first-page":"133","DOI":"10.3233\/HSM-2012-0763","article-title":"A hybrid model for time series forecasting","volume":"31","year":"2012","journal-title":"Human Systems Management"},{"issue":"2","key":"key2020032509573683000_ref049","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1080\/03088839.2018.1476741","article-title":"Forecasting container throughput based on wavelet transforms within a decomposition-ensemble methodology: a case study of China","volume":"46","year":"2019","journal-title":"Maritime Policy and Management"},{"key":"key2020032509573683000_ref050","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/j.tre.2017.08.015","article-title":"Data characteristic analysis and model selection for container throughput forecasting within a decomposition-ensemble methodology","volume":"108","year":"2017","journal-title":"Transportation Research Part E: Logistics and Transportation Review"},{"issue":"5","key":"key2020032509573683000_ref051","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","year":"2013","journal-title":"Applied Soft Computing Journal"},{"key":"key2020032509573683000_ref052","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/S0925-2312(01)00702-0","article-title":"Time series forecasting using a hybrid ARIMA and neural network model","volume":"50","year":"2003","journal-title":"Neurocomputing"},{"key":"key2020032509573683000_ref053","doi-asserted-by":"crossref","first-page":"882","DOI":"10.1016\/j.apenergy.2019.05.102","article-title":"A Kalman filter-based bottom-up approach for household short-term load forecast","volume":"250","year":"2019","journal-title":"Applied Energy"},{"key":"key2020032509573683000_ref054","doi-asserted-by":"crossref","first-page":"78063","DOI":"10.1109\/ACCESS.2019.2923006","article-title":"Short-term photovoltaic power forecasting based on long short term memory neural network and attention mechanism","volume":"7","year":"2019","journal-title":"IEEE Access"},{"issue":"2","key":"key2020032509573683000_ref055","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1080\/030888399286998","article-title":"The MED rule: the interdependence of container throughput and transshipment volumes in the Mediterranean Ports","volume":"26","year":"1999","journal-title":"Maritime Policy and Management"}],"container-title":["Industrial Management &amp; Data Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IMDS-07-2019-0370\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IMDS-07-2019-0370\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:52:46Z","timestamp":1753393966000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/imds\/article\/120\/3\/425-441\/186944"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,4]]},"references-count":56,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,12,4]]}},"alternative-id":["10.1108\/IMDS-07-2019-0370"],"URL":"https:\/\/doi.org\/10.1108\/imds-07-2019-0370","relation":{},"ISSN":["0263-5577"],"issn-type":[{"value":"0263-5577","type":"print"}],"subject":[],"published":{"date-parts":[[2019,12,4]]}}}