检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:袁婧 YUAN Jing(School of Electronic and Information Engineering,Tongji University,Shanghai 201804)
机构地区:[1]同济大学电子与信息工程学院,上海201804
出 处:《软件》2022年第1期178-180,共3页Software
摘 要:随着互联网和借贷业务的迅速发展,超前消费日趋常态化。银行信贷在满足居民消费需求、促进国民经济发展的同时,也伴随着失信行为带来的影响,给银行造成了巨大损失。借助机器学习技术建立有效的风险控制模型,做好风险防控,已成为业界的迫切需求。本文基于银行风险防控的需求,针对模型构建的需要,对相关数据集进行了统计分析和预处理,为提供模型构建所需的高质量数据样本做了前期准备。基于随机森林算法,利用集成思想的优势,建立了一种有效的风险控制模型。通过性能度量指标对模型进行评估和参数优化,并与决策树算法模型进行对比,根据最终的实验结果验证基于随机森林算法的银行风险控制模型的可行性和有效性。With the rapid development of Internet and lending business, advanced consumption is becoming more and more normal. Bank credit not only meets the consumer demand and promotes the development of national economy, but also brings the influence of dishonesty, causing huge losses to banks. With the help of machine learning technology, it has become an urgent need of the industry to establish an ef fective risk control model and do a good job in risk prevention and control. Based on the needs of bank risk prevention and control, this paper makes statistical analysis and pretreatment of relevant data sets for the needs of model building, and makes preliminary preparations for providing high-quality data samples needed for model building. Based on the random forest algorithm, an ef fective risk control model is established by taking advantage of the integrated idea. The model is evaluated and optimized by performance metrics, and compared with the decision tree algorithm model. According to the fi nal experimental results, the feasibility and ef fectiveness of the bank risk control model based on random forest algorithm are verified.
分 类 号:TP39[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.38