Data-Driven Mechanisms for a Newsvendor Problem: A Case Study

Year 2024, , 1853 - 1869, 01.12.2024

Afşin Sancaktaroğlu , Burak Gokgur , Ayşe Kocabıyıkoğlu

https://doi.org/10.35378/gujs.1334184

Abstract

Reducing food waste is paramount for a sustainable future as its implications are important to achieving sustainable development goals set by the United Nations. In many industry groups, the public awareness of reducing food waste that may potentially emerge along firms’ operations has grown. In the era of Big Data, one of the most pursued exercises of this escalating attention on reducing food waste is to utilize artificial intelligence techniques to incorporate sustainability concerns into the decision framework. Many firms embrace machine learning methods to build effective decision mechanisms that help make efficient and sustainable decisions. In this study, we analyze the impact of blending machine learning approaches with demand forecasting and order quantity decisions for a firm operating in a setting where the market demand is random, and the demand structure is not observable to the firm. The performance of the methodology is evaluated on sunflower seed demand data taken from Tadım company. Our results suggest that the joint consideration of forecasting and ordering decisions using the quantile regression approach can lead the firm to decrease its operational cost by 8,11% on average.

Keywords

Newsvendor, Machine learning, Food waste

References

• [1] Buzby, J.C., Wells, H.F. and Hyman, J., “The estimated amount, value, and calories of postharvest food losses at the retail and consumer levels in the United States”, USDA-ERS Economic Information Bulletin, 121, (2014).
• [2] Huber, J., Müller, S., Fleischmann, M., and Stuckenschmidt, H., “A data-driven newsvendor problem: from data to decision”, European Journal of Operational Research, 278(3): 904-915, (2019).
• [3] Levi, R., Roundy, R. O., and Shmoys, D.B., “Provably near-optimal sampling-based policies for stochastic inventory control models”, Mathematics of Operations Research, 32(4): 821-839, (2007).
• [4] Levi, R., Perakis, G., and Uichanco, J., “The data-driven newsvendor problem: new bounds and insights”, Operations Research, 63(6): 1294-1306, (2015).
• [5] Papanastasiou, Y., “Newsvendor decisions with two-sided learning”, Management Science, 66(11): 5408-5426, (2020).
• [6] Saghafian, S., and Tomlin, B., “The newsvendor under demand ambiguity: combining data with moment and tail information”, Operations Research, 64(1): 167-185, (2016).
• [7] Hu, J., Li, J., and Mehrotra, S., “A data-driven functionally robust approach for simultaneous pricing and order quantity decisions with unknown demand function”, Operations Research, 67(6): 1564-1585, (2019).
• [8] Ban, G.Y., and Rudin, C., “The big data newsvendor: practical insights from machine learning”, Operations Research, 67(1): 90-108, (2019).
• [9] Seubert, F., Stein, N., Taigel, F., and Winkelmann, A., “Making the newsvendor smart – order quantity optimization with ANNs for a bakery chain”, AMCIS Proceedings, (2020).
• [10] Oroojlooyjadid, A., Snyder, L.V., and Takac, M., “Applying deep learning to the newsvendor problem”, IISE Transactions, 52(4): 444-463, (2020).
• [11] Xu, L., Zheng, Y., and Jiang, L., “A robust data-driven approach for the newsvendor problem with nonparametric information”, Manufacturing & Service Operations Management, 24(1): 504-523, (2022).
• [12] Porteus, E., Foundations of Stochastic Inventory, Stanford University Press, (2002).
• [13] Silver, E. A., and Pyke, D.F., Inventory and production management in supply chain, CRC Press, Taylor & Francis Group, (2017).
• [14] James, G., Witten, D., Hastie, T., and Tibshirani, R., “An introduction to statistical learning: with applications in R”, Springer, (2013).
• [15] Breiman, L., “Random forests”, Machine Learning, 45(1): 5-32, (2001).
• [16] Chen, T., and Guestrin, C., “Xgboost: a scalable tree boosting system”, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (2016).
• [17] Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T. Y., “Lightgbm: a highly efficient gradient boosting decision tree”, Advances in Neural Information Processing Systems, 30, (2017).
• [18] Kostadinov, S., “Recurrent neural networks with Python quick start guide: sequential learning and language modeling with tensorflow”, PACKT Publishing Limited, (2018).
• [19] Yue, J., Chen, B., and Wang, M.C., “Expected value of distribution information for the newsvendor problem”, Operations Research, 54(6): 1128-1136, (2006).
• [20] Bertsimas, D., Gupta, V., and Kallus, N., “Robust sample average approximation”, Mathematical Programming, 171(1-2): 217-282, (2017).
• [21] Kleywegt, A.J., Shapiro, A., and Homem-De-Mello, T., “The sample average approximation method for stochastic discrete optimization”, SIAM Journal on Optimization, 12(2): 479-502, (2002).
• [22] Qi, M., Mak, H., and Shen, Z.M., “Data-driven research in retail operations - a review”, Naval Research Logistics, 67(8): 595-616, (2020).
• [23] Sancaktaroğlu, A., “A Data-Driven Approach to Reduce Food Waste for a Consumer Goods Company”, MSc. Thesis, Sabancı University, Sabancı Business School, İstanbul, 1-56, (2021).