预览加载中,请您耐心等待几秒...
1/10
2/10
3/10
4/10
5/10
6/10
7/10
8/10
9/10
10/10

亲,该文档总共35页,到这已经超出免费预览范围,如果喜欢就直接下载吧~

如果您无法下载资料,请参考说明:

1、部分资料下载需要金币,请确保您的账户上有足够的金币

2、已购买过的文档,再次下载不重复扣费

3、资料包下载后请先用软件解压,在使用对应软件打开

基于创新算法的理财产品个性化推荐理161203105367·理2020的基于创新算法的理财产品个性化推荐的的的的理2020基于创新算法的理财产品个性化推荐创新推荐算法的的于2015-01-282016-05-28的13647309性法的基理财产品LogisticK-Means于基于BP理财产品96.44%的算法20166的理财产品个性化推荐96.52%,理推荐算法BPK-MeansLogistic理2020PersonalizedRecommendationofFinancialProductsBasedonInnovativeAlgorithmsAbstractIntheeraofbigdata,theproblemofinformationoverloadisbecomingmoreandmoreobvious,soitisparticularlyimportanttoinnovateanddeveloprecom-mendationalgorithmstominemorevaluableinformation.Thedatainthispapermainlydependsontheservicedataofsantander’scustomersfrom2015-01-28to2016-05-28,withatotalof13647309servicerecords.Throughdatacleaning,fillinginmissingvalues,deletingduplicaterecordsanddescriptivestatistics,thedatawerepreliminarilyexplored.Usercharacteristicswereextractedbyfilteringmethod,cus-tomerportraitswereestablishedonthebasisoffeatureengineeringandpurchasebehaviorlabelsweregiventocustomers.ByLogisticregressionstudytofindoutthecharacteristicsofcustomerswhobuyannuities.Secondly,byK-Meanscluster-ingforthedatapointstodividecustomersintoactive,inactiveandthreetypesofpotentialstate,thustrendmodelbasedonBPneuralnetworktoestablishcustomerservicecometotheconclusionthataccuracyof96.44%.Finally,throughthenaivebayesalgorithminJune2016tothecustomergoingtousetheproductsofperson-alizedrecommendation,itsaccuracyis96.52%,andbasedontheconclusions,somereasonablesuggestionsarepresented.Keywords:RecommendationalgorithmBPneuralnetworkK-MeansclusteringCharacteristicsof