青岛大学学报（自然科学版）2023，Vol.36Issue(4)：133-138,6.DOI:10.3969/j.issn.1006-1037.2023.04.21
基于两步子抽样算法的贷款额影响因素研究
Research on Loan Amount Based on Two-step Sampling Algorithm
摘要
Abstract
Aiming at the problem of low efficiency of data analysis and high calculative cost caused by the loan data redundancy of Kaggle website,two-step subsampling algorithm was used to sample.Ridge re-gression model was used to fit loan amount and analyze the impact of different factors on loan amount.The results show that the loan amount is related to various factors such as the total capital payment,the number of revolving accounts,and the credit line.Compared with simple random sampling,the ridge re-gression model based on two-step sampling method reduce mean square error by 21.35%and standard er-ror by 36.79%.The two-step subsampling algorithm can effectively improve the efficiency and accuracy of data analysis.关键词
贷款额/岭回归/两步子抽样Key words
loan amount/ridge regression/two-step subsampling algorithm分类
管理科学引用本文复制引用
潘登,李莉莉..基于两步子抽样算法的贷款额影响因素研究[J].青岛大学学报（自然科学版）,2023,36(4):133-138,6.基金项目
国家社科基金(批准号:2019BTJ028)资助 （批准号:2019BTJ028）
山东省金融应用重点研究项目(批准号:2020-JRZZ-03)资助. （批准号:2020-JRZZ-03）
