研究了小额贷款公司对客户进行信用风险评估时面临的问题,构建了信用风险评估指标体系,改进了支持向量机(Support Vector Machine, SVM)对非均衡样本分类时分类超平面偏移的不足。首先分析小额贷款公司业务区域性强、信用数据来源不规范、评价标准不一致等特点,给出用于客户信用风险评估的四个维度指标。针对传统SMOTE算法在处理非均衡数据时对全部少数类样本操作的问题,提出仅对错分样本人工合成的改进思想,给出具体算法步骤。将改进算法用于某小额贷款公司客户信用风险评估案例中,分类精确度较其他算法有所提升,表明该方法的可行性和有效性。
A great number of machine learning methods have been successfully applied for customer credit risk assessment cases, and support vector machine (SVM) is considered as an "off-the-shelf" supervised learning algorithm to solve classification problem by many researchers. Unfortunately, SVM fails to provide excellent enough classification performance when the data set is imbalanced, i.e., the accuracy of the majority class is usually much higher than that of the minority class due to the shifting of the hyper-plane. In most cases, people pay more attention on the minority class such as fault diagnosis and credit default. Thus, a Synthetic Minority Over-sampling Technique (SMOTE) is presented to deal with the imbalanced classification by generating new samples in the whole minority class. However, in the process of solving SVM by Sequential Minimal Optimization (SMO) algorithm, only those support vector samples x#em/em# with the corresponding α#em/em# > 0 can affect the position of the hyper-plane while the samples far from the hyper-plane have no influence on the final result. It is obvious that the classic SMOTE algorithm can generate more redundant samples which are far from the hyper-plane. In this article, an improved method for classic SMOTE algorithm is proposed that SMOTE is looped and only misclassified samples in the previous loop are selected to be processed in the next loop until the minority class outnumbers the majority class or all minority class samples are correctly classified. In the empirical study, a data set granted by a micro-credit company in Jiangsu Province is studied. The data set originates from a company that provides loans to local individuals and enterprises for the house condition improving, farm production expanding, business operating and so on. The customers' information are analyzed according to the characteristics of micro-loan industry, and a credit risk assessment index system is suggested from four aspects with sixteen attributes in this paper. G-mean and F-measure score are used to evaluate the classification performance of the minority class, which is the accuracy of detecting default customers in this case. The results show high prediction accuracy of default customers, indicating the effectiveness of our method on credit risk assessment.
[1] Armendariz B, Morduch J.The economics of microfinance[M]. 2nd, Cambridge, MA:MIT Press, 2010.
[2] 郑毓盛, 于点默. 小额贷款的理论、实践和危机[J]. 中国农村经济, 2013, (8):88-95.
[3] Banerjee A, Chandrasekhar A G, Duflo E, et al. The diffusion of microfinance[J]. Science, 2013,341(6144).
[4] 庞素琳. 基于贷款风险损失比的农户信贷模型与应用[J]. 管理科学学报, 2012, 15(11):11-22.
[5] Yang Jian, Zhou Yinggang. Credit risk spillovers among financial institutions around the global credit crisis:Firm-level evidence[J]. Management Science, 2013, 59(10):2343-2359.
[6] Kruppa J, Schwarz A, Arminger G, et al. Consumer credit risk:Individual probability estimates using machine learning[J]. Expert Systems with Applications, 2013, 40(13):5125-5131.
[7] 张大斌, 周志刚, 许职, 等. 基于差分进化自动聚类的信用风险评价模型研究[J]. 中国管理科学, 2015, 23(4):39-45.
[8] 陈庭强, 何建敏. 基于复杂网络的信用风险传染模型研究[J]. 中国管理科学, 2014, 22(11):1-10.
[9] Moges H T, Dejaeger K, Lemahieu W, et al. A multidimensional analysis of data quality for credit risk management:New insights and challenges[J]. Information & Management, 2013, 50(1):43-58.
[10] Verbraken T, Bravo C, Weber R, et al. Development and application of consumer credit scoring models using profit-based classification measures[J]. European Journal of Operational Research, 2014, 238(2):505-513.
[11] Li Yongbin, Zhang Jianping. Approach to multiple attribute decision making with hesitant triangular fuzzy information and their application to customer credit risk assessment[J]. Journal of Intelligent & Fuzzy Systems, 2014, 26(6):2853-2860.
[12] Zhang Zhiwang, Gao Guangxia, Shi Yong. Credit risk evaluation using multi-criteria optimization classifier with kernel, fuzzification and penalty factors[J]. European Journal of Operational Research, 2014, 237(1):335-348.
[13] Marqués A I, García V, Sánchez J S. A literature review on the application of evolutionary computing to credit scoring[J]. Journal of the Operational Research Society, 2013, 64(9):1384-1399.
[14] Harris T. Credit scoring using the clustered support vector machine[J]. Expert Systems with Applications, 2015, 42(2):741-750.
[15] Sun Zhongbin, Song Qinbao, Zhu Xiaoyan, et al. A novel ensemble method for classifying imbalanced data[J]. Pattern Recognition, 2015, 48(5):1623-1637.
[16] Li Qiujie, Mao Yaobin.A review of boosting methods for imbalanced data classification[J]. Pattern Analysis and Applications, 2014, 17(4):679-693.
[17] Chawla N V, Bowyer K W, Kegelmeyer W P. SMOTE:Synthetic Minority Over-sampling Technique[J]. Journal of Artificial Intelligence Research, 2002,16:321-357.
[18] 陶新民, 郝思媛, 张冬雪,等. 基于样本特性欠取样的不均衡支持向量机[J]. 控制与决策, 2013, 28(7):978-984.
[19] 文传军, 詹永照. 基于自调节分类面SVM的平衡不平衡数据分类[J]. 系统工程, 2009, 27(3):110-114.
[20] 章少平, 梁雪春. 优化的支持向量机集成分类器在非平衡数据集分类中的应用[J]. 计算机应用, 2015, 35(5):1306-1309.
[21] 邓乃杨, 田英杰. 支持向量机——理论、方法与拓展[M]. 北京:科学出版社, 2009.
[22] Chang C C, Lin C J. LIBSVM:A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011,2(3):1-27.