Study on the Prediction of the Total Retail Amount of Consumer Goods Based on Deep Learning

DOI

10.2991/978-94-6463-710-6_9How to use a DOI?

Keywords

Dotal retail sales of consumer goods; Deep learning; Factor identification; Prediction; BiLSTM

Abstract

To address the challenges of model parameter tuning and predictive accuracy in forecasting total retail sales of consumer goods, this study introduces a novel integrated forecasting model, IDBO-VMD-BiLSTM. This model enhances the traditional dung beetle optimization algorithm (DBO) with three strategic improvements: population initialization based on the Chebyshev mapping, position updating using the golden sine operator, and theft position updating guided by dynamic weight coefficients. The efficacy of these enhancements is substantiated through benchmark function testing. Subsequently, the IDBO-VMD-BiLSTM integrated forecasting model is constructed and empirically analyzed using China’s total retail sales data from 2000 to 2021. The findings reveal that the IDBO-VMD-BiLSTM model delivers commendable predictive performance with an average absolute percentage error of 2.12%, outperforming four mainstream forecasting models. These insights contribute valuable, scientifically precise data support for the formulation of economic policies and business decision-making.

Copyright

© 2025 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  - Yanhui Li
PY  - 2025
DA  - 2025/05/14
TI  - Study on the Prediction of the Total Retail Amount of Consumer Goods Based on Deep Learning
BT  - Proceedings of the 2025 4th International Conference on Big Data Economy and Digital Management (BDEDM 2025)
PB  - Atlantis Press
SP  - 67
EP  - 74
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-710-6_9
DO  - 10.2991/978-94-6463-710-6_9
ID  - Li2025
ER  -