Machine Learning Techniques for Cafeteria Demand Forecasting: An Institutional Case
Öz
This research investigates the application of machine learning techniques for cafeteria demand forecasting within institutional settings, addressing critical operational challenges in food service management. Using a comprehensive methodological framework, the study analyzes turnstile entry data from an academic institution across November-December 2023 to develop and evaluate three complementary forecasting models: XGBoost with time-based features, Long Short-Term Memory (LSTM) networks, and Prophet models with domain-specific components. The comparative analysis reveals differentiated performance characteristics across various forecasting dimensions, with XGBoost demonstrating superior accuracy for daily forecasting (MAE=16.23, MAPE=8.32%), LSTM excelling at high-resolution 15-minute interval prediction (MAE=5.37, MAPE=11.64%), and Prophet exhibiting greater stability for extended forecast horizons. A weighted ensemble methodology integrating these complementary approaches yields consistent performance improvements across multiple evaluation metrics, achieving 4.7% reduction in daily MAE and 3.4% reduction in 15-minute interval MAE compared to the best individual models. Feature importance analysis reveals the significance of recent historical patterns, weekly cyclical components, and academic calendar effects, validating the theoretical multi-level temporal structure of institutional demand. The operational impact assessment demonstrates substantial potential benefits, including estimated food waste reduction of 6.2%, enhanced service level maintenance, and improved resource utilization. This research contributes methodological advancements through its multi-resolution forecasting framework, systematic feature engineering approach, and context-sensitive ensemble integration methodology, while providing practical implementation guidance for institutional food service operations seeking to enhance operational efficiency and sustainability through improved demand prediction.
Anahtar Kelimeler
Machine learning, Demand forecasting, Institutional catering, Time series analysis, Food waste reduction.
Kaynakça
- Athanasopoulos, G., Hyndman, R., Kourentzes, N., & Petropoulos, F. (2017). Forecasting with temporal hierarchies. In European Journal of Operational Research (Vol. 262, Issue 1, p. 60). Elsevier BV. https://doi.org/10.1016/-j.ejor.2017.02.046
- Aulia, N., & Saputro, D. R. S. (2021). Generalized Space Time Autoregressive Integrated Moving Average with Exogenous (GSTARIMA-X) Models. In Journal of Physics Conference Series (Vol. 1808, Issue 1, p. 12052). IOP Publishing. https://doi.org/10.1088/1742-6596/1808/1/012052
- Bandara, K., Hewamalage, H., Liu, Y., Kang, Y., & Bergmeir, C. (2021). Improving the accuracy of global forecasting models using time series data augmentation. In Pattern Recognition (Vol. 120, p. 108148). Elsevier BV. https://doi.org/10.1016/j.patcog.2021.108148
- Bertsimas, D., Orfanoudaki, A., & Pawlowski, C. (2020). Imputation of clinical covariates in time series. In Machine Learning (Vol. 110, Issue 1, p. 185). Springer Science+Business Media. https://doi.org/10.1007/s10994-020-05923-2
- Fayaz, S. A., Zaman, M., Kaul, S., & Butt, M. A. (2022). Is Deep Learning on Tabular Data Enough? An Assessment. In International Journal of Advanced Computer Science and Applications (Vol. 13, Issue 4). Science and Information Organization. https://doi.org/10.14569/-ijacsa.2022.0130454
- Gopalakrishna‐Remani, V., Cater, J. J., & Massey, J. J. (2016). Restaurant operations at the Rose Capital Inn: a case study exercise. In The CASE Journal (Vol. 12, Issue 1, p. 104). Emerald Publishing Limited. https://doi.org/10.1108/-tcj-11-2014-0063
- Hasan, F., Xu, K. S., Foulds, J., & Pan, S. (2021). Learning User Embeddings from Temporal Social Media Data: A Survey. In arXiv (Cornell University). Cornell University. https://doi.org/-10.48550/arxiv.2105.07996
- Huang, Q. (2021). Design and Implementation of University Central Kitchen Logistics Management System. In E3S Web of Conferences (Vol. 257, p. 2035). EDP Sciences. https://doi.org/10.1051/e3sconf/202125702035
- Hurst, A. L. M. (1997). Emerging Trends in College and University Food Service. In Journal of College & University Foodservice (Vol. 3, Issue 3, p. 17). Taylor & Francis. https://doi.org/10.1300/j278v03n03_03
- Johnston, F., & Boylan, J. E. (1996). Forecasting for Items with Intermittent Demand. In Journal of the Operational Research Society (Vol. 47, Issue 1, p. 113). Palgrave Macmillan. https://doi.org/10.1057/jors.1996.10