Pricing and Replenishment Prediction Model for Vegetable Commodities Based on Mixed Integer Linear Programming Optimization XGBoost

Shan Chen; Yuying Ma; Qiutong Wu

doi:10.54097/rps0q540

Authors

Shan Chen
Yuying Ma
Qiutong Wu

DOI:

https://doi.org/10.54097/rps0q540

Keywords:

XGBoost prediction model, mixed integer linear programming, vegetable replenishment pricing strategy.

Abstract

In fresh food superstores, the replenishment volume and pricing strategy of vegetables are affected by various factors such as seasonal seasons, supply demand, purchasing costs, and profits of vegetable categories. In this paper, we use the data related to the sales flow details and wholesale prices of each commodity from July 1, 2020 to June 30, 2023 as a dataset, and build a model based on the gradient boosting tree algorithm, XGBoost algorithm [1], to predict the total daily replenishment volume and pricing strategy of each vegetable category in the coming week (July 1-7, 2023) [2]. It is also optimized using a mixed-variable 0-1 linear programming (MILP) [3] model with decision variables including a binary variable of whether to order the vegetable category or not and a continuous variable of the number of vegetable categories ordered to compute the optimal replenishment volume and pricing strategy for July 1, 2023 for each item. Through the model in this paper, under the premise of meeting the market demand for each category of vegetable goods, while keeping the control within a specific range, the superstore can get the optimal replenishment plan and pricing strategy, reasonably allocate the resources of the warehouse space, improve the market competitiveness of the superstore, and maximize the revenue.

Downloads

Download data is not yet available.

References

Xiupeng S, Yiik D W, Michael Z L, Chandrasekar P, Chen C, et al. A feature learning approach based on XGBoost for driving assessment and risk prediction. [J], Accident; analysis and prevention, 2019, 129 ( ): 170-179.

Giulia Di Teodoro, Marta Monaci, Laura Palagi. Unboxing Tree ensembles for interpretability: A hierarchical visualization tool and a multivariate optimal re-built tree [J], arXiv (Cornell University), 2024, 12.

Djordje Dugošija, Aleksandar Savić, Zoran Maksimović. A new integer linear programming formulation for the problem of political districting [J], Annals of operations research, 2020, 288 (1): 247-263.

Milon B, Atanu S, Md. A I, Arafat J N, Shamim A, et al. Predicting Stock Market Price: A Logical Strategy using Deep Learning [J], 2021 IEEE 11th IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), 2021: 218-223.

Wei D, Yimiao H, Barry L, Guowei M, et al. XGBoost algorithm-based prediction of concrete electrical resistivity for structural health monitoring [J], Automation in Construction, 2020, 114 ( ).

Haonan Sun, Bocheng Zhang, Nian Liu. Imitation learning-based online optimal scheduling for microgrids: An approach integrating input clustering and output classification [J], IET RENEWABLE POWER GENERATION, 2023.

Amal Asselman, Mohamed Khaldi, Souhaib Aammou. Enhancing the prediction of student performance based on the machine learning XGBoost algorithm [J], Interactive Learning Environments, 2021: 1-20.

Leilei M, Chaoyong Z, Yaping R, Biao Z, Chang L, et al. Mixed-integer linear programming and constraint programming formulations for solving distributed flexible job shop scheduling problem [J], Computers & Industrial Engineering, 2020, 142 (C): 106347.

Mauricio Granada-Echeverri, Eliana M. Toro, Jhon Jairo Santa. A Mixed Integer Linear Programming Formulation for The Vehicle Routing Problem with Backhauls [J], International Journal of Industrial Engineering Computations, 2019, 10 (2): 295-308.

Pei-Ying W, Chiao-Ting C, Jain-Wun S, Wang T, Szu-Hao H, et al. Deep Learning Model for House Price Prediction Using Heterogeneous Data Analysis Along with Joint Self-Attention Mechanism [J], IEEE Access, 2021, 9: 55244-55259.