基于SARIMA模型的重庆GDP的季节预测
Forecast of Chongqing Quarterly GDP Based on SARIMA Model

对1998Q1~2021Q3的重庆GDP季度数据，利用R软体建立SARIMA模型，对建立的模型进行优化评估，并用该模型预测重庆2021的3季度GDP数据，与真实数据进行比较，以确定模型预测的准确性。根据建立的时间序列分析得到最优模型为SARIMA(2, 0, 3) × (1, 1, 0)4，预测值与实际值的平均相对误差为12.32%，SARIMA模型很好地拟合了重庆GDP的季度数据的趋势。可以利用SARIMA模型进行较准确的短期季度数据预测，为重庆经济的发展提供参考。
Based on Chongqing quarterly GDP data from 1998Q1 to 2021Q3, the SARIMA model is established by R software. The model is optimized and evaluated, and is used to predict the three quarterly GDP data of Chongqing in 2021. It is compared with the real data to determine the accuracy of the model prediction. According to the established time series analysis, the optimal model is SARIMA(2, 0, 3) × (1, 1, 0)4, and the average relative error between the predicted value and the actual value is 12.32%. SARIMA model fits the trend of Chongqing quarterly GDP data well. SARIMA model can be used to predict short-term and quarterly data accurately, which can provide reference for the economic development of Chongqing.