A Novel Hybrid STL-Based Model for Egg Price Forecasting

DOI

10.2991/978-94-6463-230-9_44How to use a DOI?

Keywords

egg price forecasting; seasonal-trend decomposition procedure based on loess; temporal convolutional network; gated recurrent unit insert; random forest

Abstract

The egg industry is a significant contributor to the economy and requires a stable egg price for its sustainable growth. Accurate egg price prediction is crucial to monitor the market, provide reference for decision-making, and achieve early warning. This study presents a novel egg price forecasting model that combines the seasonal-trend decomposition based on loess (STL), temporal convolutional network (TCN), gated recurrent unit (GRU), and random forest (RF) methods to capture the nonlinear, seasonal, and cyclical characteristics of egg price series. The egg price series is decomposed into trend, seasonal, and residual components using the STL method. Select the model with the best prediction results for the single decomposition component. So these components are then predicted using the TCN, GRU, and RF models, respectively. The predicted values are then aggregated to form the final forecast. The empirical results demonstrate that the proposed hybrid model achieves the best performance, and compared to the best predicted single model, MSE, RMSE, MAE and MAPE were reduced by 66.35%, 41.94%, 30.08% and 29.81% respectively, and R² was improved by 3.48%. This study provides a promising alternative approach for egg price forecasting, and the results have implications for the development of price forecasting techniques for other agricultural products.

Copyright

© 2023 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  - Liyun Mo
AU  - Minlan Jiang
AU  - Xiaosheng Fang
AU  - Xiaowei Shi
PY  - 2023
DA  - 2023/09/04
TI  - A Novel Hybrid STL-Based Model for Egg Price Forecasting
BT  - Proceedings of the 3rd International Conference on Internet, Education and Information Technology (IEIT 2023)
PB  - Atlantis Press
SP  - 365
EP  - 382
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6463-230-9_44
DO  - 10.2991/978-94-6463-230-9_44
ID  - Mo2023
ER  -