首页 百科知识 信用卡拖欠行为的用户特征分析

信用卡拖欠行为的用户特征分析

时间:2022-06-27 百科知识 版权反馈
【摘要】:采用流程智能技术,可以为业务流程的重要节点决策提供有用的信息和知识。例如,发行信用卡的银行在客户信用评分、交易风险预警等流程,为了掌握客户的信用等级以及进行信用风险识别和信用风险测定,需要以客户的基本资料、消费交易数据以及相关的数据为基础,建立动态的客户信用风险评估模型和欺诈预测模型。

采用流程智能技术,可以为业务流程的重要节点决策提供有用的信息和知识。例如,发行信用卡的银行在客户信用评分、交易风险预警等流程,为了掌握客户的信用等级以及进行信用风险识别和信用风险测定,需要以客户的基本资料、消费交易数据以及相关的数据为基础,建立动态的客户信用风险评估模型和欺诈预测模型。信用风险评估和欺诈预测流程如图4.21所示。

图4.21 信用风险评估和欺诈预测流程

下面对某信用卡公司信用卡风险管理流程的客户基本数据(年龄、教育程度、职业、个人年收入和信贷情况等)和消费记录,使用IBM SPSS Modeler 15中的C5.0决策树分析具有信用卡拖欠行为的用户特征,作为信用卡审批的指导。分析所用的数据放在2张Excel表格中:客户信用记录和拖欠历史记录,其中客户信用记录为5 954个样本,其中含268个欺诈样本,抽取拖欠历史记录303个样本。

大致的信用卡拖欠行为的用户特征分析如下:

(1)对客户的拖欠程度进行评估,在拖欠历史记录表中有两个字段与拖欠程度相关:拖欠总金额和逾期天数,可以将这两个字段结合起来得到拖欠程度的量化值。分别对拖欠金额和逾期天数进行打分评估,得到拖欠金额得分和拖欠时间得分,然后分别给这2个度量0.6和0.4的权重,求其加权和得到拖欠总得分。再将拖欠总得分采用分段离散化为拖欠程度的几种划分值:轻度拖欠、中度拖欠和重度拖欠。

(2)对客户信用记录表进行预处理,将其中的居住类型字段中的自购房设置为有房,租房和其他情况变换为无房。

(3)将两个数据集进行预处理合并后,以“拖欠总得分_离散”为目标,将性别、年龄、婚姻状态、户籍、教育程度、职业类别、工作年限、个人收入、保险缴纳、车辆情况和房产作为输入,选择C5.0决策树进行分析,决策树挖掘流如图4.22所示。

图4.22 C5.0决策树分析拖欠程度

(4)分析有关预测变量的重要性,可以得到个人收入对拖欠程度影响最大,年龄、户籍影响较大,教育程度、车辆情况和保险缴纳影响较小,得到的决策树如图4.23所示。

图4.23 分析拖欠程度的决策树

评估建立的决策树模型,若满足一定的正确率,就可以部署到信用卡审批管理系统的规则库。当新的交易发生时,信用卡审批管理系统就可以自动从模型库中匹配最新的欺诈模型,以进行风险分析。

参考文献

[1]Van der Aalst W M P,Weijters T,Maruster L.Workflow mining:discovering process models from event logs.IEEE Transactions on Knowledge and Data Engineering,2004,16(9):1128-1142

[2]Van der Aalst W M P.Process mining:discovery,conformance and enhancement of business processes.Berlin Heidelberg:Springer,2011

[3]Van der Aalst W M P,Adriansyah A,Medeiros A K A,et al.Process mining manifesto.Proceedings of the International Conference on Business Process Management,Clermont-Ferrand,France,2011:169-194

[4]Mans R S,Schonenberg M H,Song M,et al.Application of process mining in healthcare-a case study in a Dutch hospital.Proceedings of the International Joint Conference on Biomedical Engineering Systems and Technologies,Madeira,Portugal,2008:425-438

[5]Van der Aalst W M P,Reijers H A,Weijters A J M M,et al.Business process mining:an industrial application.Information Systems,2007,32 (5):713-732

[6]Bautista A D,Wangikar L,Akbar S M K.Process mining driven optimization of a consumer loan approvals process.Proceedings of the International Workshops on Business Process Management,Tallinn,Estonia,2012:219-220

[7]Gerke K,Mendling J,Tarmyshov K.Case construction for mining supply chain processes.Proceedings of the 12th International Conference on Business Information Systems,Poznań,Poland,2009:181-192

[8]Goedertier S,De WJ,Martens D,et al.Process discovery in event logs:an application in the telecom industry.Applied Soft Computing,2011,11 (2):1697-1710

[9]Van B N R T,Maruster L.A process mining approach to redesign business processes-a case study in gas industry.Proceedings of the International Symposium on Symbolic and Numeric Algorithms for Scientific Computing,Timisoara,2007:541-548

[10]Song M,Van der Aalst W M P.Towards comprehensive support for organizational mining.Decision Support Systems,2008,46(1):300-317

[11]Rozinat A,de Jong I S M,Gunther C W,et al.Process mining applied to the test process of wafer scanners in ASML.IEEE Transactions on Systems,Man,and Cybernetics,2009,39(4):474-479

[12]Subramaniam S,Kalogeraki V,Gunopulos D,et al.Improving process models by discovering decision points.Information Systems,2007,32 (7):1037-1055

[13]Poggi N,Muthsamy V,Carrera D,et al.Business process mining from E-commerce web logs.Proceedings of the 11th International Conference of BPM.Beijing,China,2013:65-80

[14]Gupta S.Workflow and process mining in healthcare.Technische Universiteit Eindhoven:Master's Thesis,2007

[15]Liu R,Agawal S,Sindhgatta R R,et al.Accelerating collaboration in task assignment using a socially enhanced resource model.Proceedings of the 11th International Conference on BPM.Beijing,China,2013:251-258

[16]Dustdar S,Bhattacharya K.The social compute unit.IEEE Internet Computing,2011,15(3):64-69

[17]Zeng Q,Sun S X,Duan H U A,et al.Cross-organizational collaborative workflow mining from a multi-source log.Decision support systems,2013,54(3):1280-1301

[18]Mans R,Schonenberg H,Leonardi G,et al.Process mining techniques:an application to stroke care.Studies in health technology and informatics.Amsterdam:IOS Press,2008

[19]Buijs J C A M,Van Donen B F,Van der Aalst W M P.Towards crossorganizational process mining in collections of process models and their executions.Proceedings of the International Workshops on BPM,Clermont-Ferrand,France,2012:2-13

[20]Ly L T,Rinderle S,Dadam P,et al.Mining staff assignment rules from event-based data.Proceedings of the International Workshops on BPM. Nancy,France,2006:177-190

[21]Rinderle S.Van der Aalst W M P.Life-cycle support for staff assignment rules in process-aware information systems.Technical Report,Eindhoven:Eindhoven University of Technology,2007

[22]Huang Z,Lu X,Duan H.Mining association rules to support resource allocation in business process management.Expert Systems with Applications,2011,38(8):9483-9490

[23]Bose R P J C,Van der Aalst W M P.Process mining applied to the BPI challenge 2012:divide and conquer while discerning resources. Proceedings of the International Workshops on BPM,Tallinn,Estonia,2013:221-222

[24]Liu Y,Wang J,Yang Y,et al.A semi-automatic approach for workflow staff assignment.Computers in Industry,2008,59(5):463-476

[25]Kumar A,Dijkman R M,Minseok S.Optimal resource assignment in workflows for maximizing cooperation.Proceedings of the 11th International Conference on BPM.Beijing,China,2013:4-9

[26]Nakatumba J,Van der Aalst W M P.Analyzing resource behavior using process mining.Proceedings of the International Workshops on BPM. Ulm,Germany,2010:69-80

[27]Lemos A M,Sabino C,Lima R M F,et al.Using process mining in software development process management:a case study.Proceedings of the International Conference on Systems,Man,and Cybernetics,Anchorage,AK,2011:1181-1186

[28]Jans M,Alles M,Vasarhelyi M.The case for process mining in auditing:sources of value added and areas of application.International Journal of Accounting Information Systems,2013,14(1):1-20

[29]De Weerdt J,Schupp A,Vanderloock A,et al.Process mining for the multi-faceted analysis of business processes-a case study in a financial services organization.Computers in Industry,2013,64(1):57-67

[30]赵卫东.客户智能.北京:清华大学出版社,2013

[31]赵卫东.商务智能.第三版.北京:清华大学出版社,2013

[32]Van Dongen B F,Crooy R A,Van der Aalst W M P.Cycle time prediction:when will this case finally be finished?Proceedings of the OTM Confederated International Conferencess On the Move to Meaningful Internet Systems,Monterrey,Mexico,2008:319-336

免责声明:以上内容源自网络,版权归原作者所有,如有侵犯您的原创版权请告知,我们将尽快删除相关内容。

我要反馈