Sales Forecasting Study Based on a Composite Model of Deep Learning and Random Forest

DOI

10.2991/978-94-6463-638-3_20How to use a DOI?

Keywords

Market Economy; Sales Forecasting; Big Data Analysis; Deep Learning; Random Forest

Abstract

In the current rapidly changing economic market environment, accurately forecasting sales is crucial for optimizing enterprise resources and enhancing market competitiveness. Existing prediction models often fail to fully handle complex data relationships and long-term dependencies, which limits the accuracy and practicality of the forecasts. To address these limitations, this study introduces a composite model that integrates deep learning with Random Forest (RF) to significantly enhance predictive performance. This model employs Convolutional Neural Network (CNN) to capture complex features of time-series data and uses Bidirectional Long Short-Term Memory network (BiLSTM) to manage dependencies in data both before and after, while RF reduce overfitting through multiple decision trees and achieve feature fusion through joint training, thereby optimizing prediction accuracy. Experimental results demonstrate that this model outperforms traditional models on all evaluation metrics, particularly showing exceptional adaptability in highly volatile markets with its accuracy and stability.

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  - Ziyao Wang
AU  - Yining Liu
PY  - 2024
DA  - 2024/12/30
TI  - Sales Forecasting Study Based on a Composite Model of Deep Learning and Random Forest
BT  - Proceedings of the 5th International Conference on Economic Management and Big Data Application (ICEMBDA 2024)
PB  - Atlantis Press
SP  - 200
EP  - 206
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-638-3_20
DO  - 10.2991/978-94-6463-638-3_20
ID  - Wang2024
ER  -