Sales Prediction Based on Machine Learning Approach

DOI

10.2991/978-94-6463-459-4_113How to use a DOI?

Keywords

Sales Forecast; XGBoost; LightGBM; LSTM; Model Fusion

Abstract

To help brick-and-mortar merchants set reasonable sales goals, this study proposes and implements a retail sales forecast method based on machine learning theory. Specifically, this paper used the XGBoost model, LightGBM tree structure model, long and short-term memory network (LSTM) model and model fusion method, took the sales data of 1115 physical stores of Rossmann of Germany as the research object, used three single models and three fusion models to predict sales. First, the three single models were trained and verified through feature engineering and parameter tuning; then the three single models were fused via three weighted average methods with different weights, and the fusion model was optimized and verified. Finally, two evaluation indexes, MAPE and RMSPE, were implemented to evaluate the model, and the MAPE and RMSPE values of several models were compared. Experimental results indicated that the MAPE and RMSPE values of the single model were above 0.049 and 0.065, respectively, while the MAPE and RMSPE values of the fusion model were below 0.047 and 0.062, respectively. It showed that although the single model method was effective and feasible, the fusion method effectively improved the prediction accuracy and generalization ability of the model, and obtained better performance than the single model.

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  - Yifan Sun
PY  - 2024
DA  - 2024/07/23
TI  - Sales Prediction Based on Machine Learning Approach
BT  - Proceedings of the 2024 9th International Conference on Social Sciences and Economic Development (ICSSED 2024)
PB  - Atlantis Press
SP  - 1016
EP  - 1023
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-459-4_113
DO  - 10.2991/978-94-6463-459-4_113
ID  - Sun2024
ER  -