A framework for data transformation in Credit Behavioral Scoring applications based on Model Driven Development

详细信息    查看全文

• 作者：Rosalvo Neto ; ^a ; ^b ; ^{rosalvo.oliveira@univasf.edu.br} ; Paulo Jorge Adeodato^a ; ^{pjla@cin.ufpe.br} ; Ana Carolina Salgado^a ; ^{acs@cin.ufpe.br}
• 关键词：Data mining ; Relational classification ; Credit Behavioral Scoring ; Model Driven Development
• 刊名：Expert Systems with Applications
• 出版年：2017
• 出版时间：15 April 2017
• 年：2017
• 卷：72
• 期：Complete
• 页码：293-305
• 全文大小：2485 K
• 卷排序：72

文摘

A framework to systemize the data transformation in KDD projects is proposed. The framework reduces the time of transformation with automatic code generation. The framework improves the discriminant power of data mining techniques. The framework outperforms the two main frameworks in terms of accuracy. The framework is evaluated using a public database and a private database.