基于决策树的用户信用评分模型的构建

Construction of user credit scoring model based on decision tree

信用评分系统在信用风险管理中发挥比较重要的作用,通过大数据分析技术构建评估分析模型来解决信用风险预测问题。文章在scikit-learn机器学习工具的基础上,通过利用特征选择方法生成有效特征集并结合决策树方法来构建信用评分模型,并在实际数据集得出评分结果,同时所得结果为评估人员提供信用决策建议。

Credit scoring system plays an important role in the management of credit risk. It solves the problem of credit risk prediction by constructing evaluation and analysis model through big data analysis technology. Based on the scikit-learn machine learning tool, this paper constructs a credit scoring model depended on decision tree by using the feature selection method to generate an effective feature set, and finally obtains the scoring results from the actual data set. At the same time, the results provide credit decision suggestions for the evaluators.