Abstract: In order to improve the accuracy of price prediction, factors such as the consumer price index （CPI） and economic policy uncertainty index （EPU） were incorporated into the Prophet model, and the particle swarm optimization algorithm was used to optimize the parameters. Using the daily price data from the International Garlic Trade Network, this method was applied to predict the price of garlic in Shandong Province. The results showed that the mean absolute error （MAE）, mean absolute percentage error （MAPE）, and root mean square error （RMSE） of the garlic price prediction results on the PSO-Prophet model with integrated influencing factors were reduced by 82.88%, 82.86%, and 77.49%, respectively, compared to the Prophet model. The PSO-Prophet model with integrated influencing factors could effectively improve prediction accuracy.

Key words: price forecasting, integrated influencing factors, Prophet model, PSO-Prophet model, agricultural products