부산대학교 도서관

Due to the many factors that affect commodity prices, price forecasting has become a problematic research point. With the development of machine learning and artificial intelligence, some advanced ensemble algorithms and deep learning prediction methods based on time series have high accuracy and robustness. These algorithms have gradually become the inevitable choice for solving price prediction problems. Based on the National Bureau of Statistics of China data from January 2012 to December 2021, this study proposes deep learning combined forecasting model based on neural networks to predict wheat prices and fill the research gap in agricultural product price forecasting. Researchers utilize Python and Selenium to realize the automatic data acquisition of web pages to achieve the purpose of data collection and calculation. The final price result curve predicted by the price prediction model based on LSTM deep learning agrees with the actual price curve, and the mean square error MSE is only 0.00026. It shows that this prediction model based on time series influenced by multiple factors has an excellent application prospect in price prediction.