Research on sales forecasting of fresh chicken based on ensemble learning for a broiler processing enterprise

DOI

10.2991/978-94-6463-262-0_14How to use a DOI?

Keywords

Sales forecasting; Random forest; Artificial neural network; XGBoost; Stacking

Abstract

In order to ensure the freshness of fresh food and reduce the inventory of enterprises, enterprises need to predict the sales volume of tomorrow before ordering fresh chickens. The effect of the traditional model on sales forecast is not ideal, so a sales forecast based on stacking model is proposed. Random forest and XGBoost are used as basic learners, and the artificial neural network model is used as meta-learner. Compared with the single model, the overlay fusion model is superior to other methods, with an average absolute error of 10.97, a MAPE of 83.30%, and a determination coefficient of 0.7634, which is helpful for enterprise decision-making.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Huiting Xia
AU  - Yu Cao
AU  - Xu Cheng
PY  - 2023
DA  - 2023/10/09
TI  - Research on sales forecasting of fresh chicken based on ensemble learning for a broiler processing enterprise
BT  - Proceedings of the 3rd International Conference on Management Science and Software Engineering (ICMSSE 2023)
PB  - Atlantis Press
SP  - 114
EP  - 120
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-262-0_14
DO  - 10.2991/978-94-6463-262-0_14
ID  - Xia2023
ER  -