A Vegetable-Price Forecasting Method Based on Mixture of Experts

The accurate forecasting of vegetable prices is crucial for policy formulation, market decisions, and agricultural market stability. Traditional time-series models often require manual parameter tuning and struggle to effectively handle the complex non-linear characteristics of vegetable price data,...

Full description

Saved in:
Bibliographic Details
Main Authors: Chenyun Zhao, Xiaodong Wang, Anping Zhao, Yunpeng Cui, Ting Wang, Juan Liu, Ying Hou, Mo Wang, Li Chen, Huan Li, Jinming Wu, Tan Sun
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/2/162
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832589514248290304
author Chenyun Zhao
Xiaodong Wang
Anping Zhao
Yunpeng Cui
Ting Wang
Juan Liu
Ying Hou
Mo Wang
Li Chen
Huan Li
Jinming Wu
Tan Sun
author_facet Chenyun Zhao
Xiaodong Wang
Anping Zhao
Yunpeng Cui
Ting Wang
Juan Liu
Ying Hou
Mo Wang
Li Chen
Huan Li
Jinming Wu
Tan Sun
author_sort Chenyun Zhao
collection DOAJ
description The accurate forecasting of vegetable prices is crucial for policy formulation, market decisions, and agricultural market stability. Traditional time-series models often require manual parameter tuning and struggle to effectively handle the complex non-linear characteristics of vegetable price data, limiting their predictive accuracy. This study conducts a comprehensive analysis of the performance of traditional methods, deep learning approaches, and cutting-edge large language models in vegetable-price forecasting using multiple predictive performance metrics. Experimental results demonstrate that large language models generally outperform other methods, but do not have consistent performance for all kinds of vegetables across different time scales. As a result, we propose a novel vegetable-price forecasting method based on mixture of expert models (VPF-MoE), which combines the strengths of large language models and deep learning methods. Different from the traditional single model prediction method, VPF-MoE can dynamically adapt to the characteristics of different vegetable types, dynamically select the best prediction method, and significantly improve the accuracy and robustness of the prediction. In addition, we optimized the application of large language models in vegetable-price forecasting, offering a new technological pathway for vegetable-price prediction.
format Article
id doaj-art-f8126c607ff5463586fb461e3522bac1
institution Kabale University
issn 2077-0472
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-f8126c607ff5463586fb461e3522bac12025-01-24T13:15:57ZengMDPI AGAgriculture2077-04722025-01-0115216210.3390/agriculture15020162A Vegetable-Price Forecasting Method Based on Mixture of ExpertsChenyun Zhao0Xiaodong Wang1Anping Zhao2Yunpeng Cui3Ting Wang4Juan Liu5Ying Hou6Mo Wang7Li Chen8Huan Li9Jinming Wu10Tan Sun11Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaBeijing Digital Agriculture Rural Promotion Center, Beijing 101117, ChinaBeijing Digital Agriculture Rural Promotion Center, Beijing 101117, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaThe accurate forecasting of vegetable prices is crucial for policy formulation, market decisions, and agricultural market stability. Traditional time-series models often require manual parameter tuning and struggle to effectively handle the complex non-linear characteristics of vegetable price data, limiting their predictive accuracy. This study conducts a comprehensive analysis of the performance of traditional methods, deep learning approaches, and cutting-edge large language models in vegetable-price forecasting using multiple predictive performance metrics. Experimental results demonstrate that large language models generally outperform other methods, but do not have consistent performance for all kinds of vegetables across different time scales. As a result, we propose a novel vegetable-price forecasting method based on mixture of expert models (VPF-MoE), which combines the strengths of large language models and deep learning methods. Different from the traditional single model prediction method, VPF-MoE can dynamically adapt to the characteristics of different vegetable types, dynamically select the best prediction method, and significantly improve the accuracy and robustness of the prediction. In addition, we optimized the application of large language models in vegetable-price forecasting, offering a new technological pathway for vegetable-price prediction.https://www.mdpi.com/2077-0472/15/2/162vegetable-price forecastingtime-series forecastinglarge language modelsdeep learningmixture-of-experts
spellingShingle Chenyun Zhao
Xiaodong Wang
Anping Zhao
Yunpeng Cui
Ting Wang
Juan Liu
Ying Hou
Mo Wang
Li Chen
Huan Li
Jinming Wu
Tan Sun
A Vegetable-Price Forecasting Method Based on Mixture of Experts
Agriculture
vegetable-price forecasting
time-series forecasting
large language models
deep learning
mixture-of-experts
title A Vegetable-Price Forecasting Method Based on Mixture of Experts
title_full A Vegetable-Price Forecasting Method Based on Mixture of Experts
title_fullStr A Vegetable-Price Forecasting Method Based on Mixture of Experts
title_full_unstemmed A Vegetable-Price Forecasting Method Based on Mixture of Experts
title_short A Vegetable-Price Forecasting Method Based on Mixture of Experts
title_sort vegetable price forecasting method based on mixture of experts
topic vegetable-price forecasting
time-series forecasting
large language models
deep learning
mixture-of-experts
url https://www.mdpi.com/2077-0472/15/2/162
work_keys_str_mv AT chenyunzhao avegetablepriceforecastingmethodbasedonmixtureofexperts
AT xiaodongwang avegetablepriceforecastingmethodbasedonmixtureofexperts
AT anpingzhao avegetablepriceforecastingmethodbasedonmixtureofexperts
AT yunpengcui avegetablepriceforecastingmethodbasedonmixtureofexperts
AT tingwang avegetablepriceforecastingmethodbasedonmixtureofexperts
AT juanliu avegetablepriceforecastingmethodbasedonmixtureofexperts
AT yinghou avegetablepriceforecastingmethodbasedonmixtureofexperts
AT mowang avegetablepriceforecastingmethodbasedonmixtureofexperts
AT lichen avegetablepriceforecastingmethodbasedonmixtureofexperts
AT huanli avegetablepriceforecastingmethodbasedonmixtureofexperts
AT jinmingwu avegetablepriceforecastingmethodbasedonmixtureofexperts
AT tansun avegetablepriceforecastingmethodbasedonmixtureofexperts
AT chenyunzhao vegetablepriceforecastingmethodbasedonmixtureofexperts
AT xiaodongwang vegetablepriceforecastingmethodbasedonmixtureofexperts
AT anpingzhao vegetablepriceforecastingmethodbasedonmixtureofexperts
AT yunpengcui vegetablepriceforecastingmethodbasedonmixtureofexperts
AT tingwang vegetablepriceforecastingmethodbasedonmixtureofexperts
AT juanliu vegetablepriceforecastingmethodbasedonmixtureofexperts
AT yinghou vegetablepriceforecastingmethodbasedonmixtureofexperts
AT mowang vegetablepriceforecastingmethodbasedonmixtureofexperts
AT lichen vegetablepriceforecastingmethodbasedonmixtureofexperts
AT huanli vegetablepriceforecastingmethodbasedonmixtureofexperts
AT jinmingwu vegetablepriceforecastingmethodbasedonmixtureofexperts
AT tansun vegetablepriceforecastingmethodbasedonmixtureofexperts