摘要
在线机票预订网站上的用户查询量变化是真实的民航市场需求变化的反映.通过对机票查询数据进行分析,可以准确地预测航班需求,以利于民航业做出快速的市场反应.提出了一种基于深度时空卷积神经网络的民航需求预测模型(DSTCN-FRP),将用户查询量时间序列数据转换成航线网格图,设计多层卷积神经网络来捕捉用户需求与查询数据之间的时间和空间依赖,同时加入节假日等外部因素,最后得到未来一段时间内的民航需求量.在某在线订票网站的真实查询数据集上进行了实验,结果表明:DSTCN-FRP模型优于其他现有的预测方法,其MAE比其他方法降低了15%~50%,RMSE降低了12%~28%.
The changes of users＇ query volume in online fight ticketing systems indicate the chan-ges of requirements in civil aviation market. By analyzing users＇ online query behaviors,we can accurately predict flight requirements, which is very conducive for airlines and agencies to take effective marketing actions immediately. In this paper, we propose a deep-learning-based ap-proach ,called DSTCN -FRP,to forecast flight requirements.We first transform time series data of users＇ query volumes into grid map, then design multi-layer convolution neural network to capture the time and space dependency between user requirements and query data. In addition,we further add external factors,such as weather and day of the week,to predict a period ries of flight requirements in the future. E xperiments on a real-world users＇ query dataset collect-ed from an online ticketing site demonstrate that the proposed DSTCN - FRP outperforms otherexisting forecasting methods, where its MAE falls by 15 % to 50% than other methods and RMSE falls by 12% to 28%.
作者
林友芳
康友隐
万怀宇
吴丽娜
张宇翔
LIN Youfang;KANG Youyin;WAN Huaiyu;WULina;ZH A N G Yuxian g(a.School of Computer and Information Technology,Beijing Jiaotong University,Beijing 100044,C hina,1b.Beijing Kc yLa bof Tr afficDataAnalys is and Mining,Beijing 100 04 4,China;CAAC Key Lab of Intelligent Passenger Service of Civil Aviation,Beijing 101318,China;School of Computer Science a ndTc c hnology,Civil Aviation Un iv e rs i ty of China,Tian jin 30030 0,China)
出处
《北京交通大学学报》
CAS
CSCD
北大核心
2018年第2期1-8,共8页
JOURNAL OF BEIJING JIAOTONG UNIVERSITY
基金
国家自然科学基金(61603028
U1533104)~~
关键词
民航需求预测
在线机票查询
时间序列曲线
卷积神经网络
flight requirement prediction
online flight ticket query
time series curve
convolutional neural networks
