Workload Forecasting of Warehouse Stations: Comparison Between Classical Time Series Methods and XGBoost

Main Article Content

İrem Kalafat
Mustafa Hekimoğlu
Ahmet Deniz Yücekaya
Nilay Ay
Habib Gültekin


Effective management of warehouse processes is essential in order to maintain high-level service quality and keep the costs at optimum. Each item passes through numerous workstations during their journey in warehouses from the entrepot to the shipping area. Accurate estimation of workload at stations allows personnel assignment optimization and the increase of the warehouse performance. Otherwise, it causes personnel shortages at stations, delays in shipment commitment dates and disruptions in warehouse activities. In this paper, time series forecasting models are used to estimate the load in each workstation for a better operation. The proposed methodologies are applied to an automotive spare part warehouse in Turkey. The classical time series method, which performs best in estimating the workload of each workstation, is presented and these results are compared with the XGBoost model. Thus, the models that give the best results for each station are shown. The proposed research covers part acceptance, storage, order picking and packaging processes and their substations, which were not considered in previous studies.


Download data is not yet available.

Article Details

How to Cite
İrem Kalafat, M. Hekimoğlu, A. Yücekaya, N. Ay, and H. Gültekin, “Workload Forecasting of Warehouse Stations: Comparison Between Classical Time Series Methods and XGBoost”, DataSCI, vol. 4, no. 2, pp. 19-24, Jun. 2022.
Research Articles


[1] Smith, J. The warehouse management handbook. Tompkins Press, 1998.
[2] Wiers, S. d. Warehouse manpower planning strategies in times of financial crisis: evidence from logistics service providers and retailers in the Netherlands. Production Planning & Control, 328-337, 2015.
[3] Rene´ de Koster, T. L.-D. Design and control of warehouse order picking:A literature review. European Journal of Operational Research 182, 481–501, 2007.
[4] Real Carbonneau, K. L. Application of machine learning techniques for supply chain demand forecasting. European Journal of Operational Research 184, 1140–1154, 2008.
[5] Chin-Chia Jane, Y.-W. L. A clustering algorithm for item assignment in a synchronized zone order picking system. European Journal of Operational Research 166, 489–496, 2005.
[6] Koo, P.-H. The use of bucket brigades in zone order picking systems. OR Spectrum 31(4), 759-774, 2009.
[7] Teun Van Gils, K. R. The Use of Time Series Forecasting in Zone Order Picking Systems to Predict Order Pickers' Workload. International Journal of Production Research, Vol. 55 No. 21, 6380-6393, 2017.
[8] Thai Young Kim, R. D. Improving warehouse labour efficiency by intentional forecast bias. International Journal of Physical Distribution & Logistics Management, 2018.
[9] Dinis, D., Barbosa-Póvoa, A., & Teixeira, Â. P. Enhancing capacity planning through forecasting: An integrated tool for maintenance of complex product systems. International Journal of Forecasting, 38(1), 178-192, 2022.
[10] Tasquia Mizan, S. T. A causal model for short‐term time series analysis to predict incoming Medicare workload. Journal of Forecasting, 228– 242, 2021.
[11] Olya, M. H., Badri, H., Teimoori, S., & Yang, K. An integrated deep learning and stochastic optimization approach for resource management in team-based healthcare systems. Expert Systems with Applications, 187, 115924, 2022.
[12] Piccialli, F., Giampaolo, F., Salvi, A., & Cuomo, S.. A robust ensemble technique in forecasting workload of local healthcare departments. Neurocomputing, 444, 69-78, 2021.
[13] S. Papadopoulos, I. K. IEEE Power and Energy Conference at Illinois (PECI). Short-term Electricity Load Forecasting using Time Series and Ensemble Learning Methods, 1-6, 2015.
[14] Liao, X., Cao, N., Li, M., & Kang, X. International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS). Research on Short-Term Load Forecasting Using XGBoost Based on Similar Days, 675-678, 2019.
[15] Raza Abid Abbasi, N. J. Short Term Load Forecasting Using XGBoost. Advances in Intelligent Systems and Computing, 1120-1131,2019.
[16] Khan, T., Tian, W., Ilager, S., & Buyya, R. Workload forecasting and energy state estimation in cloud data centres: ML-centric approach. Future Generation Computer Systems, 128, 320-332, 2022.
[17] Kumar, J., & Singh, A. K. Performance evaluation of metaheuristics algorithms for workload prediction in cloud environment. Applied Soft Computing, 113, 107895, 2021.
[18] Bartholdi, J. a. Warehouse & Distribution Science,2019.
[19] Kwiatkowski, Denis & Phillips, Peter C. B. & Schmidt, Peter & Shin, Yongcheol, Testing the null hypothesis of stationarity against the alternative of a unit root : How sure are we that economic time series have a unit root?. Journal of Econometrics, Elsevier, vol. 54(1-3), pages 159-178,1992.
[20] Hyndman, R. J., & Athanasopoulos, G. Forecasting: Principles and Practice. 2nd ed. Otexts, 2018.
[21] Holt, C. C. Forecasting seasonals and trends by exponentially weighted averages. O.N.R. Memorandum No. 52, 1957.
[22] Tianqi Chen, C. G. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785-794, 2016.