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

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, w...