集成机器学习模型在不平衡样本财务预警中的应用
2021年电子技术应用第8期
张 露1,刘家鹏1,江敏祺2
1.中国计量大学 经济与管理学院,浙江 杭州310018;2.上海财经大学 信息管理与工程学院,上海200000
摘要: 基于上交所主板市场A股企业的财务指标数据来预测企业的财务风险,样本数据包括1 227家正常上市企业和42家被财务预警的企业,数据严重不平衡,通过重采样技术解决了分类器在不平衡样本中失效的问题,运用Bagging思想的集成机器学习对预测模型进行提升与优化。正确挑选出有财务危机企业的概率最高达到92.86%,在此基础上,样本的整体准确率在经过模型的集成之后提高了5.4%。集成模型提高了对上市企业的财务预警能力,能为企业的正常经营和投资者的安全投资提供一定的借鉴。
中图分类号: TN99;TP391
文献标识码: A
DOI:10.16157/j.issn.0258-7998.201234
中文引用格式: 张露,刘家鹏,江敏祺. 集成机器学习模型在不平衡样本财务预警中的应用[J].电子技术应用,2021,47(8):34-38.
英文引用格式: Zhang Lu,Liu Jiapeng,Jiang Minqi. The application of the integrated machine learning model in the financial crisis of imbalanced sample[J]. Application of Electronic Technique,2021,47(8):34-38.
文献标识码: A
DOI:10.16157/j.issn.0258-7998.201234
中文引用格式: 张露,刘家鹏,江敏祺. 集成机器学习模型在不平衡样本财务预警中的应用[J].电子技术应用,2021,47(8):34-38.
英文引用格式: Zhang Lu,Liu Jiapeng,Jiang Minqi. The application of the integrated machine learning model in the financial crisis of imbalanced sample[J]. Application of Electronic Technique,2021,47(8):34-38.
The application of the integrated machine learning model in the financial crisis of imbalanced sample
Zhang Lu1,Liu Jiapeng1,Jiang Minqi2
1.School of Economics and Management,China Jiliang University,Hangzhou 310018,China; 2.School of Information Management and Engineering,Shanghai University of Finance and Economics,Shanghai 200000,China
Abstract: This paper forecast the financial risk of enterprises based on the financial index data of A-share enterprises in the main board market of Shanghai Stock Exchange.The samples included 1227 normal listed enterprises and 42 enterprises which have been financial warning. The data was seriously unbalanced. The problem of classifier failure in unbalanced samples was solved by resampling technology in some certain.The integrated machine learning based on Bagging was used to improve and optimize the prediction model.The highest probability of correctly selecting enterprises with financial warning was 92.86%. On this basis, the overall accuracy of the sample was improved by 5.4% after the integration of the model. The integrated model improved the financial early warning ability of listed enterprises which could provide some reference for the normal operation of enterprises and the safety investment of investors.
Key words : financial early warning prediction;integrated machine learning;imbalanced sampling technology
0 引言
进入大数据时代以来,对信息的敏感程度和预测能力变得尤为重要,而对企业而言,无论是在经营活动还是投资活动中,财务危机预警一直是个问题和难题。机器学习的兴起为大数据的处理和应用提供了新的方式。
目前,许多学者将机器学习与金融危机预警相结合,取得了重大突破。OHLSON J A[1]建议将逻辑回归应用于分类的后概率,来估计公司的破产概率。Zou Hui和HASTIE T[2]提出了弹性网络,克服了岭回归和Lasso的缺点[3]。决策树学习是一种强大的分类器[4],在树分类器的基础上,有学者提出了随机森林[5]和XGBoost[6],在计算机[7]、图像分类[8]等领域被证明有效。
但在过去的研究中,大多采用人工设定样本量,而忽视了实际上财务预警企业与正常企业的数量对比的悬殊[9]。数据不平衡的问题是财务预警研究领域的难题[10]。VEGANZONES D和SEVERIN E[11]提出采样技术可用于提高不平衡样本预测的分类器性能,随机上采样技术[12]、随机下采样技术[13]和人工合成少数抽样技术(SMOTE)[14]的应用解决了集成复杂分类器在不平衡的财务预警研究数据中失效的问题。而集成学习机制可以通过集成不同的模型来整合多种算法的优点[15],目前在个人信贷领域已经有了一定的应用[16]。
本文详细内容请下载:http://www.chinaaet.com/resource/share/2000003695。
作者信息:
张 露1,刘家鹏1,江敏祺2
(1.中国计量大学 经济与管理学院,浙江 杭州310018;2.上海财经大学 信息管理与工程学院,上海200000)
此内容为AET网站原创,未经授权禁止转载。