基于VMD-SSA-LSTM模型的水果价格预测研究

作     者：李巧 

作者机构：贵州大学数学与统计学院贵州 贵阳 

出 版 物：《电子商务评论》 (E-Commerce Letters)

年 卷 期：2025年第14卷第1期

页      面：1752-1760页

学科分类：0202[经济学-应用经济学] 02[经济学] 020205[经济学-产业经济学] 

主　　题：水果价格 VMD-SSA-LSTM 价格预测 

摘      要：水果作为我国种植业中第四大农作物类别,在国民经济中占据着十分重要的地位,水果的价格波动不仅影响居民生活成本,也影响果农的收入。因此,预判水果价格的走势十分重要。文中选取2021年第22周至2024年第38周,共计174周的红富士苹果、巨峰葡萄和麒麟西瓜这三种水果的周度批发价格数据,建立VMD-SSA-LSTM模型,并与LSTM、VMD-LSTM模型的水果价格预测效果进行对比,实验发现,VMD-SSA-LSTM模型的预测值最接近真实值,且其RMSE、MAE、MAPE的数值均小于LSTM、VMD-LSTM模型的数值,表明VMD-SSA-LSTM模型的预测效果优于LSTM、VMD-LSTM模型。Fruits are the fourth largest crop category in China’s agricultural sector and play a vital role in the national economy. The fluctuations in fruit prices not only affect the cost of living for residents but also affect the income of fruit farmers. Therefore, it is crucial to forecast the trend of fruit prices. In this study, we selected the weekly wholesale prices of Red Fuji apples, Jufeng grapes, and Qilin watermelons from week 22 of 2021 to week 38 of 2024, a total of 174 weeks, and built the VMD-SSA-LSTM model to predict the prices of these three fruits. We also compared the fruit price prediction effects of the VMD-SSA-LSTM model with those of the LSTM and VMD-LSTM models. The experimental results show that the predicted values of the VMD-SSA-LSTM model are closest to the actual values, and its RMSE, MAE, and MAPE values are all smaller than those of the LSTM and VMD-LSTM models, indicating that the prediction effect of the VMD-SSA-LSTM model is better than that of the LSTM and VMD-LSTM models.