摘要
针对当前电子商务移动支付风险预测方法存在效率低、偏差大等弊端,为了提高电子商务移动支付风险预测精度,提出数据挖掘技术的电子商务移动支付风险预测模型。首先,收集电子商务移动支付风险一维时间序列数据,并将其重构成一个多维的电子商务移动支付风险时间序列;然后,采用数据挖掘技术对多维的电子商务移动支付风险时间序列进行分析,构建电子商务移动支付风险预测模型;最后,采用Matlab 2019平台上,与其他电子商务移动支付风险预测模型进行对比实验,结果表明文中方法的电子商务移动支付风险预测偏差很小,可以高精度跟踪电子商务移动支付风险变化特点,而且电子商务移动支付风险预测的效率很高,预测效果显著优于其他电子商务移动支付风险预测模型,验证了该电子商务移动支付风险预测模型的可行性。
The current e⁃commerce mobile payment risk prediction method has some disadvantages like low efficiency and large deviation.Therefore,an e⁃commerce mobile payment risk prediction model based on data mining technology is proposed to improve its risk prediction accuracy.The one⁃dimensional time series data of e⁃commerce mobile payment risk is collected and reconstructed into a multi⁃dimensional time series of e⁃commerce mobile payment risk,which is then analyzed by data mining technology to build the e⁃commerce mobile payment risk prediction model.Experiments were performed on platform Matlab 2019 to make comparison between the proposed model and other models.The results show that the prediction deviation of the proposed model is very small.The proposed model can track the change characteristics of e⁃commerce mobile payment risk accurately and predict risk efficiently with significantly better risk prediction effect than other models,which verifies its feasibility.
作者
秦莹
QIN Ying(Wuzhou University,Wuzhou 543000,China)
出处
《现代电子技术》
北大核心
2020年第21期106-109,113,共5页
Modern Electronics Technique
基金
2020年度广西高校中青年教师科研基础能力提升项目(2020KY17006)
梧州学院校级基金项目(2018B007)。
关键词
电子商务时代
电子交易
支付风险管理
数据挖掘技术
多维时间序列
风险预测
e⁃commerce era
e⁃transaction
payment risk management
data mining technology
multidimensional time series
risk prediction
