A Study on Vegetable Sales Forecasting Based on Seasonal Indices and LSTM Model
DOI:
https://doi.org/10.54097/yhmd9x32Keywords:
SVR Model, Seasonal Indices and LSTM Model, Vegetable Sales Forecast, Machine Learning.Abstract
Efficient food supply chain management is crucial for the perishable and seasonally affected vegetable sales field due to global population growth and urbanization acceleration. This trend has led to the widespread application of data analytics and machine learning technologies for optimizing pricing strategies and predicting sales trends. This study aims to explore the relationship between the total sales volume of a vegetable category and its cost-plus pricing using the Pearson correlation coefficient analysis method. Additionally, it seeks to establish a support vector regression (SVR) model and an improved long short-term memory network (LSTM) model based on seasonal index prediction. The projected purchase volume of mosaic and leafy vegetables for the next 7 days is 135.47, 135.65, 127.00, 125.26, 83.11, 105.29, and 157.34 kg. Finally, this dissertation formulated a purchase strategy for the upcoming week based on the predicted sales volume. We calculated the 7-day profit margins to be 0.80, 0.61, 0.62, 0.77, 0.63, 0.57, 0.63. This analysis offers a theoretical foundation for enhancing operational efficiency and profit levels in the vegetable sales sector, as well as practical guidance.
Downloads
References
Jiang Dan. Research on consumer behavior analysis and market dynamic pricing model of agricultural products[D]. Northeast Agricultural University, 2014.
Wang Xiaotong. Research on inventory control strategy of fresh fruit and vegetable products in supermarket chains based on DIT[D]. Southeast University,2020.
Wang Ruogang. Problems and countermeasures of food safety management in agricultural supply chain[J]. China Food Industry, 2024,(01):95-97.
Mao Lisha. Research on pricing strategy and production and marketing model of vegetable wholesale market under the perspective of supply chain[D]. Central South Forestry University of Science and Technology,2022.
Lv Wang. Research on trend prediction of fresh vegetables sales based on improved SVM[D]. Anhui Agricultural University, 2021.
Yang Ruiming,WANG Fuji,GUO Qianjin,et al. Research on fresh vegetable consumption of plantation structural adjustment in the context of agricultural supply side structural reform--Based on gray correlation analysis method[J]. Economist,2021,(10):37-39+42.
Sun Kun, Research on demand forecasting of food supply chain based on machine learning [D]. North China Electric Power University (Beijing),2020.
Zhang Qianqian. Research on vegetable demand forecasting system based on SVM [D]. Beijing Jiaotong University,2015.
Nie Yuxuan. Research on automatic pricing and replenishment strategy of fresh commodities based on ARIMA prediction optimization model--taking vegetable commodities as an example[J]. Commercial Exhibition Economy,2024,(05):19-22.
Cui Yunhao,Zhu Jun,Meng Hao. Application of neural network in sales forecasting of agricultural products[J]. Modern Agricultural Science and Technology,2021,(17):262-266.
Cui Yunhao. Research on fresh vegetables sales prediction based on CNN-PSO-LSTM combination model[D]. Anhui Agricultural University,2022.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
