基于统计方法的异常点检测在时间序列数据上的应用  

Application of statistical methods in outlier detection for time series data

作　　者：曹晨曦 田友琳 张昱堃 刘晓峰 CAO Chenxi;TIAN Youlin;ZHANG Yukun;LIU Xiaofeng(College of Mathematics,Taiyuan University of Technology,Taiyuan 030024,China;College of Software,Nankai University,Tianjin 300071,China)

机构地区：[1]太原理工大学数学学院,山西太原030024 [2]南开大学软件学院,天津300071

出　　处：《合肥工业大学学报（自然科学版）》2018年第9期1284-1288,共5页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(61502330)

摘　　要：异常点是时间序列数据中不可避免的特殊点,会对时间序列数据的分析产生负面影响。文章设计了一种适用于时间序列数据的基于统计的异常点检测与修正方法,可以有效地检测出异常点出现的位置并进行修正。使用酒店间夜数据进行的数值实验表明,使用修正后的数据集相对于使用原数据集预测精度会提高3.4%～4.4%。The outliers are unavoidable anomalous points in time series data.It will affect the accuracy of time series data.In this paper,a method of outlier detection and correction for time series data based on statistics is designed,which can effectively detect the position of anomalous points and make correction.The results of the numerical experiment on hotel room night data show that the accuracy of the compressed dataset is improved by 3.4%to 4.4%compared with that of the original dataset.

关 键 词：收益管理 预测 异常点 统计 压缩 

分 类 号：O213.9[理学—概率论与数理统计]