Computer Engineering and Applications ›› 2019, Vol. 55 ›› Issue (2): 221-227.DOI: 10.3778/j.issn.1002-8331.1709-0387

Previous Articles     Next Articles

NOSHOW Prediction and Strong Factor Association Analysis in Civil Aviation

CAO Weidong1,2, XU Daidai2, WANG Jing2, WANG Jialiang2   

  1. 1.Tianjin Key Lab for Advanced Signal and Image Processing, Civil Aviation University of China, Tianjin 300300, China
    2.College of Computer Science and Technology, Civil Aviation University of China, Tianjin 300300, China
  • Online:2019-01-15 Published:2019-01-15

民航NOSHOW预测及强因子关联分析

曹卫东1,2,许代代2,王  静2,王家亮2   

  1. 1.中国民航大学 天津市智能信号与图像处理重点实验室,天津 300300
    2.中国民航大学 计算机科学与技术学院,天津 300300

Abstract: In business of civil aviation, the phenomenon that passengers cannot be scheduled after reservations(NOSHOW) has been the unsolved problem in terms of airline revenue loss. In order to solve the problem, a method of NOSHOW prediction and strong factor association analysis in civil aviation is proposed. Firstly, the NOSHOW decision tree is modeled by improved C5.0 algorithm, and the quantified results of NOSHOW correlation factor are obtained. Then, the association rule mining of NOSHOW strong factor is carried out by Apriori algorithm. The NOSHOW decision tree model with accuracy of 99.75% is constructed, and 139 factor association rules with confidence above 80.054% and support over 10.021% are obtained, which further reveals the implicit correlation relationship between NOSHOW strong factors, besides it also provides an effective decision-making basis for major airlines to implement accurate NOSHOW prediction and revenue enhancement management.

Key words: NOSHOW prediction, improved C5.0 algorithm, decision tree model, Apriori algorithm, strong factor correlation analysis

摘要: 在民航业务中,旅客订座后却不能如期登机(NOSHOW)一直是航空公司收益亏损的未解之题,为了解决该问题,提出了一种民航NOSHOW预测及强因子关联分析方法。首先利用优化C5.0算法进行NOSHOW决策树建模,得到了NOSHOW相关因子的量化结果,然后通过Apriori算法对NOSHOW强因子进行关联规则挖掘。实验构建了准确率为99.75%的NOSHOW决策树模型,得到了139条置信度在80.054%以上、支持度在10.021%以上的因子关联规则,进一步揭示了NOSHOW强因子之间的隐含关联关系,为各大航空公司实现准确的NOSHOW预测及收益提升管理提供了有效的决策依据。

关键词: NOSHOW预测, 优化C5.0算法, 决策树建模, Apriori算法, 强因子关联分析