基于混合遗传算法-支持向量机的中小型企业信用评估模型

Credit evaluation model of small and medium-sized enterprises based on HGA-SVM

为准确评估中小型企业的信用等级和风险状况,提出了一种混合遗传算法(Hybrid Genetic Algorithm,HGA),该算法针对遗传算法后期局部搜索能力差、收敛速度慢等缺陷,对标准遗传算法的遗传算子进行了研究和改进.通过引入退火选择、多模式交叉变异等遗传算子,加强了遗传算法的收敛性和准确性,并将改进的HGA算法应用于支持向量机(Support Vector Machine,SVM)参数的优化,构建了HGA-SVM信用评估模型.实验结果表明:与传统的评估方法以及目前主流的机器学习评估模型相比,HGA-SVM信用评估模型在收敛速度以及评估精准度上有着明显改善,提升了信用风险的评估效果.

In order to accurately evaluate the credit rating and risk status of small and medium enterprises,a hybrid genetic algorithm is proposed.Aimed at the defects of poor local search ability and slow convergence speed in the later stage of GA,the algorithm researched and improved the genetic operator of the standard genetic algorithm.By introducing genetic operators such as annealing selection,multimode crossover mutation,the convergence and accuracy of the genetic algorithm are enhanced,and the improved HGA algorithm is applied to the parameter optimization of support vector machines to construct the HGA-SVM credit evaluation model.Experimental results show that compared with traditional evaluation methods and current mainstream machine learning evaluation models,the HGA-SVM credit evaluation model has significantly improved convergence speed and evaluation accuracy.The classification success rate has significantly improved the evaluation effect of credit risk.