Automatic Pricing and Replenishment Decision for Vegetable Commodities Based on Support Vector Regression

Yiqi Liu; Siyu Yi; Boxu Song

doi:10.62051/vbhpa724

Authors

Yiqi Liu
Siyu Yi
Boxu Song

DOI:

https://doi.org/10.62051/vbhpa724

Keywords:

Support Vector Regression, Prediction Model, Replenishment Decision.

Abstract

Automated pricing and replenishment decisions for vegetable merchandise play a critical role in the retail industry. Accurate pricing and replenishment forecasts can effectively improve operational efficiency, reduce inventory costs, and increase customer satisfaction. In order to accurately realize the automatic pricing and replenishment decisions, paper use the recent 30-day data to forecast the future based on the cost-plus pricing method, taking into account the seasonality of vegetable commodities, and at the same time, taking into account the cyclicality of vegetable commodities, paper use the sales volume of the previous year in the same month to fit the sales volume of the coming week, and combine the weighting of ARIMA time-series forecasting results to get the final forecasted sales volume, and employ the SUPPORT VECTOR REGRESSION theory to calculate the pricing, using the loss rate to calculate the replenishment, and finally constructed the automatic pricing and replenishment decision model for vegetable commodities applicable to big data, and the results show that the choice of cost-plus ratio is relatively stable, and the standard deviation of the sample is 0.24, which can help hypermarkets to achieve better decision-making.

Downloads

Download data is not yet available.

References

[1] Chiru C G, Posea V V. Time series analysis for sales prediction [C]//Artificial Intelligence: Methodology, Systems, and Applications: 18th International Conference, AIMSA 2018, Varna, Bulgaria, September 12–14, 2018, Proceedings 18. Springer International Publishing, 2018: 163-172.

[2] Aalto H. Competition-Based Dynamic Pricing in E-Commerce [D]., 2019.

[3] Fan G F, Guo Y H, Zheng J M, et al. A generalized regression model based on hybrid empirical mode decomposition and support vector regression with back‐propagation neural network for mid‐short‐term load forecasting [J]. Journal of Forecasting, 2020, 39(5): 737-756.

[4] Zhang F, O'Donnell L J. Support vector regression [M]//Machine learning. Academic Press, 2020: 123-140.

[5] Benvenuto D, Giovanetti M, Vassallo L, et al. Application of the ARIMA model on the COVID-2019 epidemic dataset[J]. Data in brief, 2020, 29: 105340.

[6] Peck R, Short T, Olsen C. Introduction to statistics and data analysis [M]. Cengage Learning, 2020.

[7] Barusman A R P, Yuliana T M, Mirfazli E. Analysis of implementation cost plus pricing method in the decision on the determination of product sales Prices [J]. Intern J Adv Sci Techn, 2020, 29(06): 1832-1838.

[8] Tiara T, Maulidia Y, Kantun S. The Pricing Evaluation Using the Cost-Plus Pricing Method at CV Macarindo Berkah Group in Jember District [J]. RIGGS: Journal of Artificial Intelligence and Digital Business, 2023, 2(1): 6-11.

[9] Wang Y G, Wu J, Hu Z H, et al. A new algorithm for support vector regression with automatic selection of hyperparameters [J]. Pattern Recognition, 2023, 133: 108989.

[10] Zhang T, Zhang Z, Chi Y. Research on Vegetable Replenishment Strategy Based on Time Series Analysis [J]. Information Systems and Economics, 2024, 5(1): 74-81.

[11] Wang W, Luo Y, Yang X. Automated pricing and replenishment strategies for vegetable products based on SVR and simulated annealing [J]. International Journal of Global Economics and Management, 2024, 2(3): 1-10.