Abstract: The traditional model can not capture uranium resource price’s comprehensive trend，because of unsteady and nonlinear time-series data.The forecasting model based on the combination of Autoregressive Integrated Moving Average（ARIMA） and Support Vector Machine（SVM） is built to improve the prediction accuracy of the model in this paper and PSO algorithm is used to optimize the parameters of SVM.The proposed model is applied to uranium resource price tendency forecasting example，and the simulation results show that the forecasting performance of the hybrid model outperforms single ARIMA and SVM ahead forecasting.

Key words: Autoregressive Integrated Moving Average（ARIMA）, Support Vector Machine（SVM）, combination forecasting, uranium resource price

摘要： 由于国际铀资源价格时间序列数据的非线性性与非平稳性，使用单一的预测模型很难捕捉到其综合趋势。为了进一步提高模型的预测精度，建立了基于差分自回归移动平均（ARIMA）和支持向量机SVM的组合预测模型，并用PSO算法对SVM模型中的参数进行优化。将该方法应用于实际铀资源价格预测，并与单一的ARIMA模型和SVM模型进行比较。仿真实验结果表明，该组合预测模型实现了对铀资源价格数据更为准确的预测。

关键词: 差分自回归移动平均, 支持向量机, 组合预测, 国际铀资源价格