摘要
提高航空客运需求预测的准确性对于航空公司以及整个航空运输系统的发展都具有重要的现实意义。以往研究普遍采用单一分解策略去处理航空客运需求时序中存在的复杂特征,以此提升组合模型的预测性能。然而传统的分解策略存在着特征提取不完全、分解方法带有固有缺陷等问题,导致组合模型预测效果不能得到充分的提升。为此,本文提出一种基于二次分解策略和模糊时间序列模型的航空客运需求预测方法。该方法首先利用季节调整模型(X12-ARIMA)将原始时序分解成季节成分序列与季节调整后序列,继而利用改进的自适应噪声集成经验模态分解方法(ICEEMDAN)将季节调整后序列分解成一系列不同时间尺度的本征模态函数(IMF)和残差序列(Residue)。然后使用基于模糊C均值算法(FCM)划分论域区间的FTS模型对季节成分序列、各IMF分量以及残差序列分别进行预测。最后将各分量序列的预测结果进行集成,重构出航空客运需求的预测值。实证结果表明,本文所提出的二次分解策略表现显著优于传统的分解策略,并且本文所提出模型对于航空客运需求预测有着较高的准确性。
Improving the accuracy of air passenger demand forecasting plays a crucial role in the development of airlines and the whole air transport system,which is of great political and economic significance for all of society but is still a challenging task.In previous studies,individual decomposition strategy has been adopted generally to deal with the complex features inair passenger demand series,so as to improve the prediction performance of the hybrid model.However,the traditional decomposition strategy has some drawbacks such as incomplete feature extraction and the inherent defects in the decomposition method,which lead to the inadequate improvement of the prediction effect of the hybrid model.Therefore,a method for air passenger demand forecasting based on a dual decomposition strategy and a fuzzy time series modelis proposed.Firstly,a seasonal adjustment model(X12-ARIMA)is applied to decompose the original series into a seasonal component and a seasonally adjusted series.Then the improved complete ensemble empirical mode decomposition with adaptive noise(ICEEMDAN)is used to decompose the seasonally adjusted series into several intrinsic mode functions(IMFs)with different time scales and a residue.After that,the FTS model with fuzzy c-means algorithm(FCM)partitioning intervals is used to forecast each IMF component,the residue and the seasonal component.Finally,the prediction of air passenger traffic is obtained by integrating the above results.Case studies utilizing monthly air passenger demand data collected from Shanghai Pudong International Airport,Chengdu Shuangliu International Airport and Shenzhen Bao’an International Airport are employed as examples.The empirical results show that the dual decomposition strategy proposed in this paper is significantly better than the traditional decomposition strategy,and the proposed model outperforms all of the considered comparison models.The proposed model can be used to improve the accuracy of air passenger demand prediction.
作者
梁小珍
耶志坤
杨明歌
汪寿阳
LIANG Xiao-zhen;WU Zhi-kun;YANG Ming-ge;WANG Shou-yang(School of Management,Shanghai University,Shanghai 200444,China;School of Economics and Management,University of Chinese Academy of Sciences,Beijing 100190,China;Academy of Mathematics and Systems Science,Chinese Academy of Sciences,Beijing 100190,China)
出处
《中国管理科学》
CSSCI
CSCD
北大核心
2020年第12期108-117,共10页
Chinese Journal of Management Science
基金
国家自然科学基金资助项目(71701122,71702095,11801352)。
关键词
航空客运需求预测
季节调整
自适应噪声集成经验模态分解
模糊C均值算法
模糊时间序列模型
forecast of air passenger demand
seasonal adjustment
improved complete ensemble empirical mode decomposition with adaptive noise
fuzzy c-means algorithm
fuzzy time series model