论文部分内容阅读
机器算法中存在许多不同类型和方式的运行模式,而在诸多算法之中,集成学习的算法是一种基于统计理论以计算机实现的良好机器学习方法.阐述了集成学习的基本思想和实现步骤,运用Bagging集成学习算法试图建立一个个人信用评估模型,以期取得更好的预测结果.运用信息增益法筛选指标,采用V折交叉确认法,利用UCI的信用数据对单个分类器、Bagging集成分类器模型的分类精度和稳健性进行试验比较.结果表明,Bagging-决策树有效的提高了样本的精确性,在个人信用评估的分析中占有较强的优势.
Among many algorithms, the integrated learning algorithm is a good machine learning method based on statistical theory and computer.The paper elaborates the basic thought and the realization steps of integrated learning, Bagging integrated learning algorithm is used to establish a personal credit evaluation model in order to get a better prediction result.Improved the index by using the information gain method, using the V-fold cross-validation method, UCI credit data for a single classifier, Bagging integrated classifier model The classification accuracy and the robustness of the proposed method are compared.The results show that the Bagging-decision tree effectively improves the accuracy of the sample and occupies a strong advantage in the analysis of personal credit rating.