基于麻雀搜索算法与随机森林融合模型的个人信用评估
Personal credit evaluation based on sparrow search algorithm and random forest fusion model
王培培 1周小平 1陈佳佳 1李浩1
作者信息
- 1. 上海师范大学 信息与机电工程学院,上海 201418
- 折叠
摘要
针对如何准确评估复杂的用户信用问题,提出一种基于麻雀搜索算法的随机森林(SSA-RF)模型,利用SSA优化RF模型中决策树和最小节点数,并基于优化后的RF模型对数据样本进行分类,并评估所提模型和传统模型的性能.研究结果表明:SSA-RF模型具备较高的准确性.
Abstract
A random forest(RF)based on sparrow search algorithm(SSA-RF)model was proposed to accurately evaluate complex user credit problems.SSA was used to optimize the number of decision trees and minimum number of nodes in the RF model,and the optimized RF model was used to classify data samples.The performances of the proposed model and traditional model were evaluated.The research results indicated that the SSA-RF model had higher accuracy.
关键词
信用风险评估/特征选择/随机森林(RF)模型/麻雀搜索算法(SSA)Key words
credit risk assessment/feature selection/random forest(RF)model/sparrow search algorithm(SSA)引用本文复制引用
基金项目
上海市科学技术委员会项目(22142201900)
出版年
2024
NETL
NSTL
万方数据