Research on supermarket replenishment volume prediction based on LSTM and PSO algorithm

Ke Yan; Daxuanrui Deng

doi:10.54097/e8w01s21

Authors

Ke Yan
Daxuanrui Deng

DOI:

https://doi.org/10.54097/e8w01s21

Keywords:

LSTM algorithm apriori model PSO particle swarm optimization algorithm prediction model.

Abstract

In order to meet people's health needs and reduce economic losses, the new fresh suppliers carried out real, reliable and targeted market demand analysis so that they formulate automatic pricing and replenishment decision of vegetable commodities with the aim of providing fresh and nutritious vegetable commodities. This paper adopts the apriori model to explore the correlation between vegetables and reflects the relationship between total sales and cost plus pricing by the linear fitting method.This paper further uses the LSTM time series prediction model, time sliding sequence and PSO particle swarm algorithm to predict the various vegetable categories of daily supplement and pricing in the next week, so as to maximize the business super profit. The results showed that the price of each vegetable category had a significant negative correlation with the sales volume and the dynamic prediction of replenishment quantity and pricing data had obvious application effect, which effectively helped the supermarket to make pricing and replenishment decisions.

Downloads

Download data is not yet available.

References

Zhao Y, Zheng R. Combination of Fruit and Vegetable Storage and Fresh-Keeping with Postharvest Heat Treatment[J]. Journal of Chemistry, 2022, 2022.

Cao Tingting, Zeng Kaifang, Deng Lili. Progress of application of light technology in storage and preservation of fruits and vegetables [J]. Food and fermentation industry, 48(10): 314-320.

Cao Yu, Xu Rongliang, Hu Hanli, et al. Research on the joint replenishment strategy of vending machines in unmanned retail industry [J]. Chinese management science, 2021, 29(11): 179-190.

Kiil K, Dreyer H C, Hvolby H H, et al. Sustainable food supply chains: the impact of automatic replenishment in grocery stores[J]. Production Planning & Control, 2018, 29(2): 106-116.

Wang F, Lin L. Spare parts supply chain network modeling based on a novel scale-free network and replenishment path optimization with Q learning[J]. Computers & Industrial Engineering, 2021, 157: 107312.

Sharma S, Abouee‐Mehrizi H, Sartor G. Inventory management under storage and order restrictions[J]. Production and Operations Management, 2020, 29(1): 101-117.

Chen W N, Tan D Z. Set-based discrete particle swarm optimization and its applications: a survey[J]. Frontiers of Computer Science, 2018, 12: 203-216.

Feng J, Li C. PSO-optimization method of joint replenishment problem with fuzzy requirement[J]. Jisuanji Gongcheng yu Yingyong(Computer Engineering and Applications), 2012, 48(35): 238-242.

Bai X , Jia J , Wei Q ,et al.Association rule mining algorithm based on Spark for pesticide transaction data analyses[J].International Journal of Agricultural and Biological Engineering, 2019(5).

Zhang R, Chen W, Hsu T C, et al. ANG: a combination of Apriori and graph computing techniques for frequent itemsets mining[J]. The Journal of Supercomputing, 2019, 75: 646-661.

Amaral J V, Guerreiro R. Factors explaining a cost-based pricing essence[J]. Journal of Business & Industrial Marketing, 2019, 34(8): 1850-1865.

Ren X, Liu S, Yu X, et al. A method for state-of-charge estimation of lithium-ion batteries based on PSO-LSTM[J]. Energy, 2021, 234: 121236.