摘要
针对助学贷款额度小、管理过程繁琐、违约率高的问题,提出了用基于支持向量机的助学贷款信用风险预警系统来有效降低关注范围、提高贷后管理效率的方法.在分析助学贷款违约影响因素和相关预警模型特点的基础上,建立了支持向量机预警模型;通过实际数据测试,模型在违约和守约分类预测方面有较高的准确率,为银行调整贷后管理策略提供了依据.
Considering the small amounts, the tedious management process and the high default rate of student loans, this paper proposes a student loans credit risk warning system based on the support vector machine to effectively reduce the scope of attention for loans and improve their management efficiency. On the basis of an analysis of the factors contributing to defaulting and the characteristics of an early warning model, an early warning model based on the support vector machine （SVM） is built. Actual data tests show that the model has a high accuracy rate in the prediction of contract observance and breach and can provide a basis for banks to adjust loan management strategies.
出处
《五邑大学学报（自然科学版）》
CAS
2014年第1期50-53,共4页
Journal of Wuyi University(Natural Science Edition)
基金
广东省哲学社会科学规划项目(GD11XGL20)
