基于铁路出行数据的旅客常住地智能识别算法研究
|
摘要
常住地是判断旅客消费能力与收入水平的重要因素,利于根据旅客常住地进行个性化产品推荐。针对铁路客票发售与预订系统的海量出行数据,依据逻辑判断与概率计算设计了铁路旅客常住地智能识别算法;最后利用Scala语言在铁路客运大数据平台上实现算法,并针对最近两年铁路旅客出行数据进行案例验证,结论表明:该算法有效,旅客常住地信息的识别率为67.7%。
Permanent residence is an important factor of passenger's consumption ability and income level, which is conducive to accomplish personalized recommendation. According to the travel data of Railway Ticketing and Reservation System, this article designed an intelligent recognition algorithm to infer the railway passenger's permanent residence through logical judgment and probability statistics, used Scala language to implement algorithm on large data platform of railway passenger transport. Based on the case study of railway passenger travel data in recent two years, the conclusion shows that the algorithm is effective and the recognition rate of passenger permanent residence is 67.7%.
Permanent residence is an important factor of passenger's consumption ability and income level, which is conducive to accomplish personalized recommendation. According to the travel data of Railway Ticketing and Reservation System, this article designed an intelligent recognition algorithm to infer the railway passenger's permanent residence through logical judgment and probability statistics, used Scala language to implement algorithm on large data platform of railway passenger transport. Based on the case study of railway passenger travel data in recent two years, the conclusion shows that the algorithm is effective and the recognition rate of passenger permanent residence is 67.7%.
引文
[1]武洁,李桂芝.我国各地区常住人口总量推算方法探讨[J].统计研究,2011,28(2):76-80.
[2]杨杰.上海流动人口特征及其空间差异性分析[D].上海:华东师范大学,2013.
[3]余欣甜.我国分区域人口迁移流动的动态和特点[D].上海:复旦大学,2014.
[4]许亮,邓文胜.基于GIS的武汉城市圈常住人口空间分布研究[J].资源开发与市场,2007,23(2):112-115.
[5]Jeffrey Dean,Sanjay Ghemawat.MapReduce:Simplified Data Processing on Large Clusters[J].COMMUNICATIONS OFTHE ACM,2008,51(1):101-113.
[6]靳鑫元.基于移动通信大数据的人口流动性测度研究[D].太原:山西财经大学,2017.
[7]单杏花,王富章,朱建生,等.铁路客运大数据平台架构及技术应用研究[J].铁路计算机应用,2016,25(9):14-16.
[8]吕晓艳,刘彦麟,单杏花.基于大数据平台的铁路旅客群体分析应用研究[J].铁路计算机应用,2016,25(9):28-30.
[9]逄锦波,武博.基于Logistic模型的青岛常住人口预测[J].山东科技大学学报(自然科学版),2008,27(3):102-108.
[10]李翔,陈振杰,吴洁璇,等.基于夜间灯光数据和空间回归模型的城市常住人口格网化方法研究[J].地球信息科学学报,2017,19(10):1298-1305.
[2]杨杰.上海流动人口特征及其空间差异性分析[D].上海:华东师范大学,2013.
[3]余欣甜.我国分区域人口迁移流动的动态和特点[D].上海:复旦大学,2014.
[4]许亮,邓文胜.基于GIS的武汉城市圈常住人口空间分布研究[J].资源开发与市场,2007,23(2):112-115.
[5]Jeffrey Dean,Sanjay Ghemawat.MapReduce:Simplified Data Processing on Large Clusters[J].COMMUNICATIONS OFTHE ACM,2008,51(1):101-113.
[6]靳鑫元.基于移动通信大数据的人口流动性测度研究[D].太原:山西财经大学,2017.
[7]单杏花,王富章,朱建生,等.铁路客运大数据平台架构及技术应用研究[J].铁路计算机应用,2016,25(9):14-16.
[8]吕晓艳,刘彦麟,单杏花.基于大数据平台的铁路旅客群体分析应用研究[J].铁路计算机应用,2016,25(9):28-30.
[9]逄锦波,武博.基于Logistic模型的青岛常住人口预测[J].山东科技大学学报(自然科学版),2008,27(3):102-108.
[10]李翔,陈振杰,吴洁璇,等.基于夜间灯光数据和空间回归模型的城市常住人口格网化方法研究[J].地球信息科学学报,2017,19(10):1298-1305.