STL-ATTLSTM: Vegetable Price Forecasting Using STL and Attention Mechanism-Based LSTM

• Published in: Agriculture (Basel) Vol. 10; no. 12; p. 612
• Main Authors: Yin, Helin, Jin, Dong, Gu, Yeong Hyeon, Park, Chang Jin, Han, Sang Keun, Yoo, Seong Joon
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.12.2020
• Subjects: Accuracy; Agricultural production; Agriculture; attention mechanism; Back propagation; cabbage; Climate change; Consumers; Crop production; Decomposition; Deep learning; Forecasting; Garlic; Genetic algorithms; hot peppers; loess; Long short-term memory; LSTM; Machine learning; markets; Mathematical models; Meteorological data; Model accuracy; Neural networks; onions; prediction; Predictions; Prices; Pricing; radishes; Regression analysis; Root-mean-square errors; Seasonal variations; Statistical methods; STL; Supply & demand; Support vector machines; Time series; time series analysis; Trends; vegetable price forecasting; Vegetables; Weather; China
• DOI: 10.3390/agriculture10120612
• ISSN: 2077-0472

It is difficult to forecast vegetable prices because they are affected by numerous factors, such as weather and crop production, and the time-series data have strong non-linear and non-stationary characteristics. To address these issues, we propose the STL-ATTLSTM (STL-Attention-based LSTM) model, which integrates the seasonal trend decomposition using the Loess (STL) preprocessing method and attention mechanism based on long short-term memory (LSTM). The proposed STL-ATTLSTM forecasts monthly vegetable prices using various types of information, such as vegetable prices, weather information of the main production areas, and market trading volumes. The STL method decomposes time-series vegetable price data into trend, seasonality, and remainder components. It uses the remainder component by removing the trend and seasonality components. In the model training process, attention weights are assigned to all input variables; thus, the model’s prediction performance is improved by focusing on the variables that affect the prediction results. The proposed STL-ATTLSTM was applied to five crops, namely cabbage, radish, onion, hot pepper, and garlic, and its performance was compared to three benchmark models (i.e., LSTM, attention LSTM, and STL-LSTM). The performance results show that the LSTM model combined with the STL method (STL-LSTM) achieved a 12% higher prediction accuracy than the attention LSTM model that did not use the STL method and solved the prediction lag arising from high seasonality. The attention LSTM model improved the prediction accuracy by approximately 4% to 5% compared to the LSTM model. The STL-ATTLSTM model achieved the best performance, with an average root mean square error (RMSE) of 380, and an average mean absolute percentage error (MAPE) of 7%.