Yanting Liao, Chufeng Yang, Sisi Zheng*
School of Mathematics and Statistics, Huizhou University, Huizhou, Guangdong, China.
*Corresponding author:Sisi Zheng
Abstract
As the first line of defense of the enterprise supply chain, product demand forecast plays an important role in enterprises in different industries, so it is of research value to forecast it accurately. This paper preprocesses the product demand data set of a large domestic manufacturing enterprise, and through the exploration of data characteristics, it is concluded that seven different variables have a certain influence on product demand. Using feature engineering, a new column is constructed, and it is coded by single heat and map mapping. By using lag features and window statistics, 49 data features are constructed and screened. Four machine learning models, such as XGBoost, LightGBM, decision tree regression, and random forest, are constructed respectively, and the parameters are compared vertically with the grid parameters. Three indexes, mean square error (MSE), root mean square error (RMSE) and determinable coefficient (R2) are selected to evaluate the model. Accurate estimation can reduce the inventory cost of enterprises and make a pricing scheme with higher information content.
References
[1] Zhou Huiting. Study on Optimization of pigment supply Chain Demand Management of B Company [D]. Shanghai International Studies University, 2022.
[2] Wei Wei, He Leiyong, Li Chuihui. Demand forecasting method of electric locomotive products based on genetic algorithm and grey neural network [J]. Packaging Engineering, 2022, 43(12):37-44.
[3] Wu Gengqi, Niu Dongxiao, Geng Shiping, et al. Product Demand Forecasting of Manufacturing Enterprises Based on Deep Learning Algorithm from Multi-value chain perspective [J]. Science Technology and Engineering, 2021, 21(31):13413-13420.
[4] Rui Si. The 11th "Teddy Cup" Data Mining Challenge [EB/OL].
https://www.tipdm.org:10010 /#/competition/1620719578957127680/question. [2023-05-20].
[5] m0_59138290. Map mapping. https://blog.csdn.net/m0_59138290/article/details/127562412 [2023.05.21].
[6] Xu Jiang, Zhang Hongyu, Li Junhuai, et al. Parallel processing of streaming data based on Sliding window [J]. Heavy Machinery, 2021, (01):29-36.
[7] Zhu Fuxi. Artificial Intelligence [M]. 3rd edition. Beijing: Tsinghua University Press, 2012.
[8] Cai Jingbo, Cai Zhijie. Prediction of high turnover in the A-share market based on Machine learning Model [J]. Mathematical Modeling and Application, 2020, 9(04):74-84.
[9] Lu Weimin, Sun Chenfeng, Ren Likun, et al. An aero-engine Gas-path Fault Diagnosis Method Based on CN-LGBM [J]. Journal of Armaments, 2023: 1-11.
[10] Yu Yuan. Decision Tree-Regression: https://zhuanlan.zhihu.com/p/42505644. [2023.05.21]
How to cite this paper
Product Demand Forecasting Based on LGBM Deep Learning Models
How to cite this paper: Yanting Liao, Chufeng Yang, Sisi Zheng. (2024) Product Demand Forecasting Based on LGBM Deep Learning Models. Journal of Applied Mathematics and Computation, 8(1), 83-87.
DOI: http://dx.doi.org/10.26855/jamc.2024.03.010