Research on cold chain logistics demand forecast based on LSTM model

Authors

  • Xin Feng School of Economics and Management, Southwest Petroleum University, Chengdu, China

DOI:

https://doi.org/10.54097/e7tft511

Keywords:

Cold chain logistics, Demand forecast, LSTM long short-term memory network

Abstract

Cold chain logistics demand is affected by multiple factors and exhibits significant nonlinear, dynamic and time series dependence characteristics. Traditional forecasting methods are difficult to accurately capture its long-term changing patterns, resulting in large deviations in forecast results. In order to improve the accuracy of cold chain logistics demand forecasting and optimize industry resource allocation, infrastructure construction and development planning, this article takes the total national cold chain logistics demand as the research object, selects 12 core indicators from macroeconomics, population consumption, industry development and other dimensions as influencing factors, collects relevant statistical data from 2005 to 2024, and builds a cold chain logistics demand forecasting model based on long short-term memory network (LSTM). The core parameters of the LSTM model are optimized based on time series characteristics, and the prediction accuracy of the model is verified through three indicators: root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Research has confirmed that the LSTM model has excellent applicability and accuracy in cold chain logistics demand forecasting, and its prediction results can effectively support the scientific and intelligent development of the cold chain logistics industry.

Downloads

Download data is not yet available.

References

[1] Li, G. X., Ma, W. B., & Xia, G. E. (2021). Research on logistics demand forecast model based on deep learning. Journal of Systems Science, 29(2), 85–89. (In Chinese)

[2] Ran, Y. Z. (2021). Logistics demand forecast in Guizhou Province based on deep learning model. Logistics Engineering and Management, 43(6), 19–20+18. (In Chinese)

[3] Ran, M. L., Chen, Y. R., & Yang, X. B. (2022). Short-term logistics demand forecast based on EEMD-LMD-LSTM-LEC deep learning model. Control and Decision, 37(10), 2513–2523. (In Chinese)

[4] Wang, M. T. (2023). Research on cold chain logistics demand forecast [Master’s thesis]. Shanxi University of Finance and Economics. (In Chinese)

[5] Wang, Z. Y., & Zhang, Z. Q. (2024). Comparative study on the performance of LSTM and GRU models in predicting logistics demand in Hubei Province. Logistics Engineering and Management, 46(4), 10–14. (In Chinese)

[6] Guo, W. Y., Li, Y. T., Bai, K. C., et al. (2025). Cold chain logistics demand forecast for fresh products based on deep learning. Logistics Research, (2), 75–83. (In Chinese)

[7] Li, S. C., & Ye, J. (2022). Analysis and prediction of agricultural product cold chain logistics demand based on gray regression model. Highway Transportation Technology, 39(5), 166–174. (In Chinese)

[8] Zhang, Z. (2025). Research on Cold Chain Logistics Demand Forecast of Fresh Agricultural Products in Hubei Province [Master’s thesis]. Jianghan University. (In Chinese)

[9] Wei, X. (2024). Research on demand forecasting of cold chain logistics of agricultural products based on artificial neural network [Master’s thesis]. Shenyang University of Technology. (In Chinese)

[10] Duncombe, J. U. (1959). Infrared navigation—Part I: An assessment of feasibility (Periodical style). IEEE Transactions on Electron Devices, ED-11, 34–39.

[11] Du, L. J., & Zhang, Y. L. (2025). Analysis of high-quality development paths of cold chain logistics. China Storage and Transportation, (10), 117. (In Chinese)

Downloads

Published

14-10-2026

Issue

Section

Articles