Date of Graduation
5-2026
Document Type
Thesis
Degree Name
Bachelor of Science
Degree Level
Undergraduate
Department
Data Science
Advisor/Mentor
Karl D. Schubert
Committee Member
Karl Schubert
Second Committee Member
James Lezon
Third Committee Member
Scott Wheatley
Abstract
This project develops and evaluates a predictive modeling framework for forecasting distribution center capacity utilization at Company Y, with monthly forecast horizons up to one year. Motivated by the operational challenges of seasonal demand volatility, promotional cycles, and the absence of a formally defined capacity metric, the study first constructs a historical capacity utilization measure from raw warehouse management system data — reconciling item volumes, location dimensions, and utilization factors across all DCs — which serves as the target variable for all modeling work. Four models are developed and evaluated against a naïve seasonal baseline: SARIMA, LightGBM, LSTM, and a hybrid forecast-simulation model. Models are assessed on mean absolute error, root mean square error, and mean absolute percentage error. SARIMA achieved the strongest standalone accuracy and is selected as the primary forecasting tool, producing native confidence intervals that provide the same richness of probabilistic output as the hybrid model’s Monte Carlo simulation while offering greater simplicity and interpretability. The hybrid model, which integrates probabilistic forecasting with a simulation of DC operational processes, was evaluated but not selected, as its confidence interval outputs do not provide meaningful additional planning value over SARIMA’s native intervals and its added complexity is not justified by its accuracy performance. Results demonstrate that data-driven capacity forecasting is achievable from existing WMS data and establishes a scalable foundation for future enhancements including real-time WMS integration, richer demand signals, and expanded probabilistic outputs.
Keywords
Capacity Utilization, Distribution, Supply Chain, Time Series Forecasting, Machine Learning
Citation
Shortt, J. J. (2026). A Forecasting Framework for Distribution Center Capacity Utilization: An Applied Industry Study. Data Science Undergraduate Honors Theses Retrieved from https://scholarworks.uark.edu/dtscuht/41
Included in
Business Analytics Commons, Business Intelligence Commons, Data Science Commons, Industrial Engineering Commons, Operational Research Commons, Operations and Supply Chain Management Commons
