A hybrid SARIMA. and support vector machines in forecasting the production values of the machinery industry in Taiwan
A hybrid SARIMA. and support vector machines in forecasting the production values of the machinery industry in Taiwan
复制标题
DOI：
10.1016/j.eswa.2005.11.027
复制
发表时间：
2007-01-01
影响因子：
8.5
通讯作者：
Wang, Cheng-Hua
中科院分区：
文献类型：
--
作者：
Chen, Kuan-Yu;Wang, Cheng-Hua
本文提出了一种混合方法，利用季节性自回归积分移动平均（SARIMA）模型和支持向量机（SVM）模型在预测季节性时间序列方面的独特优势。使用台湾机械工业产值的季节性时间序列数据来检验所提出的混合模型的预测准确性。比较了混合模型、SARIMA 模型和 SVM 模型三种模型的预测性能。在这些方法中，混合模型的归一化均方误差（NMSE）和平均绝对百分比误差（MAPE）最低。混合模型还能够预测测试时间序列的某些重要转折点。 (C) 2005 Elsevier Ltd. 保留所有权利。
This paper proposes a hybrid methodology that exploits the unique strength of the seasonal autoregressive integrated moving average (SARIMA) model and the support vector machines (SVM) model in forecasting seasonal time series. The seasonal time series data of Taiwan's machinery industry production values were used to examine the forecasting accuracy of the proposed hybrid model. The forecasting performance was compared among three models, i.e., the hybrid model, SARIMA models and the SVM models, respectively. Among these methods, the normalized mean square error (NMSE) and the mean absolute percentage error (MAPE) of the hybrid model were the lowest. The hybrid model was also able to forecast certain significant turning points of the test time series. (C) 2005 Elsevier Ltd. All rights reserved.