Forecasting Retail Sales Via the Use of Stacking Model

DOI

10.2991/978-94-6463-036-7_59How to use a DOI?

Keywords

machine learning; predict; models; stacking

Abstract

Nowadays, the march of machine learning brings about the improvements of companies’ ability to respond the changes in the marketplace and enables them to balance more easily the supply and demand. Thus, predicting based on historical data is getting more and more prevalent. There are numerous approaches applied to attain better results in this research area. The data in this research is from Kaggle and is genuine data provided by 1C company. This paper adopts six models, i.e., Linear Regression, Ridge regression, Random Forest, GBDT, XGBOOST and Stacking to forecast the future sales of retail products based on the historical data. The root mean square error between the real and anticipated data is utilized as performance evaluation. And the results show that the stacking method presents the best performance.

Copyright

© 2022 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  - Che Sun
PY  - 2022
DA  - 2022/12/31
TI  - Forecasting Retail Sales Via the Use of Stacking Model
BT  - Proceedings of the 2022 2nd International Conference on Economic Development and Business Culture (ICEDBC 2022)
PB  - Atlantis Press
SP  - 405
EP  - 411
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-036-7_59
DO  - 10.2991/978-94-6463-036-7_59
ID  - Sun2022
ER  -