基于C-AdaBoost模型的乳腺癌预测研究

机器学习和深度学习技术可用于解决医学分类预测中的许多问题,其中一些分类算法的预测精度较高,而另一些算法的精度有限。提出了基于C-AdaBoost模型的集成学习算法,对乳腺癌疾病进行预测,发现了判断乳腺癌是否复发、乳腺癌肿瘤是否为良性的最优特征组合。通过逐步回归方法对现有特征进行二次选取,并结合C-AdaBoost模型使得预测效果更优。大量实验表明,基于C-AdaBoost模型的算法的预测准确率比SVM、Naive Bayes、RandomForest以及传统的集成学习模型等机器学习分类器的准确率最多可提高19.5%,从而可以更好地帮助医生进行临床决策。     

基于新闻文本的上市公司财务困境组合预测模型

已有上市公司财务困境预测模型主要是基于结构化数据进行研究,为进一步提高上市公司财务困境预测模型准确率,本文将非结构化数据引入上市公司财务困境预测问题中,研究了基于新闻文本分类的上市公司财务困境预测模型,结合新闻文本信息和财务信息提出上市公司财务困境组合预测模型。本文首先将新闻数据进行预处理,然后基于新闻文本数据通过支持向量机（SVM）进行财务困境预测,同时基于财务数据通过Logistic模型进行财务困境预测,最后采用阈值表决集成策略整合两种模型的预测结果,实验结果证明了模型的有效性。     

贝叶斯优化的XGBoost信用风险评估模型

信用风险评估是银行和其他金融机构信贷审批业务中必不可少的一环。为进一步提高信用风险评估的准确率和模型可解释性,提出了基于贝叶斯优化的极端梯度提升树（extreme gradient boosting,XGBoost）信用风险评估模型。XGBoost集成学习模型预测准确率高,基学习器采用树模型,易于可视化,具有良好的可解释性。然而,XGBoost模型超参数众多,模型效果依赖于超参数的精确设置。在这项研究中,采用贝叶斯高斯过程（GP）作为XGBoost的超参数优化器,并与网格搜索、随机搜索进行比较研究。所提出的模型在三个信用贷款数据集上进行训练和测试,选择准确率和F1分数等四项指标评价模型性能。实验结果发现将贝叶斯高斯过程用于XGBoost模型的超参数优化,收敛速度快。所提出的模型在三个数据集上的准确率比表现最好的对比模型分别高出3.5、3.62和0.91个百分点。     

一种改进过采样算法在类别不平衡信用评分中的应用

针对信贷行业信用评分业务中存在的样本类别不平衡问题,首先在信用评分各影响因素Fisher比率值分析的基础上确定主要评判指标;而后以基于支持度的过采样算法（SDSMOTE）为样例合成算法,支持向量机（SVM）为基预测器,Boosting算法为框架构建基于Fisher-SDSMOTE-ESBoostSVM的类别不平衡信用评分预测模型;并在基分类器训练结束后引入“淘汰策略”,删除未被正确分类的合成样例,重新生成正类样例并修正样例权重;最后以UCI数据库中德国信用数据集为实验样本,F-measure值和G-mean值为评价指标,对比分析Fisher-SDSMOTE-ESBoostSVM与其他集成学习算法的预测结果。实验结果表明,Fisher-SDSMOTE-ESBoostSVM算法应用到信贷行业客户信用评分预测中具有可行性和适应性,且预测准确率较高,具有一定的实际应用价值。     

极限学习机的分类器集成模型研究

将极限学习机算法与旋转森林算法相结合,提出了以ELM算法为基分类器并以旋转森林算法为框架的RF-ELM集成学习模型。在8个数据集上进行了3组预测实验,根据实验结果讨论了ELM算法中隐含层神经元个数对预测结果的影响以及单个ELM模型预测结果不稳定的缺陷;将RF-ELM模型与单ELM模型和基于Bagging算法集成的ELM模型相比较,由稳定性和预测精度的两组对比实验的实验结果表明,对ELM的集成学习可以有效地提高ELM模型的性能,且RF-ELM模型较其他两个模型具有更好的稳定性和更高的准确率,验证了RF-ELM是一种有效的ELM集成学习模型。     

基于AdaBoost-BOA的中小企业信用评估模型

针对我国现有信贷风险评估体系的不完善以及银行对中小企业的信用等级评估的要求,提出了一种基于Ada?Boost-BOA的中小企业信用评估模型.首先确定中小企业信用评估指标,然后通过贝叶斯优化算法构建AdaBoost-BOA集成分类信用评估模型.实验结果表明,与其他传统的模型相比较,论文提出的AdaBoost-BOA模型在信用等级评估中具有更优良的评估性能,其准确率更高.     

基于SVM的房贷信用评估的应用研究

信贷风险是金融机构风险主要来源.支持向量机(SVM)在解决两类问题上是一种较好的分类方法,其学习模型有较强的稳定性.对SVM在房贷信用评估应用中的问题进行了研究和解决,如核函数选取,参数选取,样本非均衡问题等.实验得出在实际应用中径向基模型较好,采用Grid-search方法调整参数,能达到更好的推广能力和预测结果,用分别惩罚支持向量机能有效解决样本非均衡问题.试验结果也证明了基于SVM的房贷信用评估方法优于原有的打分方法.     

基于支持向量机的机载吊舱故障诊断优化算法

提升机载吊舱的后勤保障能力,适应吊舱测试中多型号、多故障类型和测试环境动态变化的测试要求,是打赢现代化战争的重要保障。支持向量机（SVM）算法适用于小样本、高维度、非线性分类问题,SVM相关参数是影响算法性能的重要因素。基于K-CV算法和粒子群算法两种改进的SVM模型可以实现SVM参数优化,K-CV算法可以交叉验证优化模型参数,粒子群算法可以对SVM参数进行动态寻优,建立多核SVM吊舱故障诊断模型。两种算法都可以提高吊舱故障诊断模型的准确率,提高模型的学习能力和泛化能力,有效对吊舱的故障进行定量和定位诊断。     

一种基于Bagging-SVM的智能传感器集成学习方法

集成多个传感器的智能片上系统( SoC)在物联网得到了广泛的应用.在融合多个传感器数据的分类算法方面,传统的支持向量机( SVM)单分类器不能直接对传感器数据流进行小样本增量学习.针对上述问题,提出一种基于Bagging-SVM的集成增量算法,该算法通过在增量数据中采用Bootstrap方式抽取训练集,构造能够反映新信息变化的集成分类器,然后将新老分类器集成,实现集成增量学习.实验结果表明:该算法相比SVM单分类器能够有效降低分类误差,提高分类准确率,且具有较好的泛化能力,可以满足当下智能传感器系统基于小样本数据流的在线学习需求.     

组合模型在商业银行信用风险评估中的研究

研究商业银行信用风险评估问题,商业银行信用风险评评估涉及指标相当多,各指标间呈非线性关系且存在严重冗余信息,传统评估方法不能很好消除冗余信息,只能反映指标间的线性关系,导致风险评估准确率低.为了提高商业银行信用风险评估的准确性,提出了一种粗糙集理论(Rs)和BP神经网络(BPNN)相结合的商业银行信用风险评估组合模型(RS_BPNN).新模型首先利用粗糙集理论对各评估指标进行指标约筒,消除指标间的冗余消息,简化神经网络的网络结构,然后将约简后的数据输入非线性预测能力优异的BP神经网络进行训练,得到商业银行信用风险评估模型,最后采用中国工商银行某分行数据对组合模型进行仿真试验.仿真结果表明,与传统的BP神经网络模型相比,组合模型加快了网络的运算速度,提高风险评估准确率,获得评估结果更具科学性.     

Least squares support vector machines ensemble models for credit scoring

Due to recent financial crisis and regulatory concerns of Basel II, credit risk assessment is becoming one of the most important topics in the field of financial risk management. Quantitative credit scoring models are widely used tools for credit risk assessment in financial institutions. Although single support vector machines (SVM) have been demonstrated with good performance in classification, a single classifier with a fixed group of training samples and parameters setting may have some kind of inductive bias. One effective way to reduce the bias is ensemble model. In this study, several ensemble models based on least squares support vector machines (LSSVM) are brought forward for credit scoring. The models are tested on two real world datasets and the results show that ensemble strategies can help to improve the performance in some degree and are effective for building credit scoring models.     

A hybrid ensemble approach for enterprise credit risk assessment based on Support Vector Machine

Enterprise credit risk assessment has long been regarded as a critical topic and many statistical and intelligent methods have been explored for this issue. However there are no consistent conclusions on which methods are better. Recent researches suggest combining multiple classifiers, i.e., ensemble learning, may have a better performance. In this paper, we propose a new hybrid ensemble approach, called RSB-SVM, which is based on two popular ensemble strategies, i.e., bagging and random subspace and uses Support Vector Machine (SVM) as base learner. As there are two different factors, i.e., bootstrap selection of instances and random selection of features, encouraging diversity in RSB-SVM, it would be advantageous to get better performance. The enterprise credit risk dataset, which includes 239 companies’ financial records and is collected by the Industrial and Commercial Bank of China, is selected to demonstrate the effectiveness and feasibility of proposed method. Experimental results reveal that RSB-SVM can be used as an alternative method for enterprise credit risk assessment.     

一种混合的信用卡欺诈检测模型

信用卡欺诈检测是一个重要的问题,为了提升对于真实世界的信用卡欺诈数据的识别率,提出了一种混合的信用卡欺诈检测模型AWFD(Anomaly weight of credit card fraud detection),首先通过异常检测的方法将数据划分为可信和异常数据,然后利用半监督的方法训练一个集成模型,最终再利用异常检测进一步剔除检测结果中的异常结果。AWFD在保障对于可信数据的学习效果上,通过半监督集成学习的方法,利用异常数据进一步扩充集成模型的多样性,并将异常检测和集成模型融合。实验结果表明,比起一些传统的机器学习方法,AWFD可以提高整体的信用卡欺诈检测的识别率。     

A novel hybrid credit scoring model based on ensemble feature selection and multilayer ensemble classification

Credit scoring focuses on the development of empirical models to support the financial decision‐making processes of financial institutions and credit industries. It makes use of applicants' historical data and statistical or machine learning techniques to assess the risk associated with an applicant. However, the historical data may consist of redundant and noisy features that affect the performance of credit scoring models. The main focus of this paper is to develop a hybrid model, combining feature selection and a multilayer ensemble classifier framework, to improve the predictive performance of credit scoring. The proposed hybrid credit scoring model is modeled in three phases. The initial phase constitutes preprocessing and assigns ranks and weights to classifiers. In the next phase, the ensemble feature selection approach is applied to the preprocessed dataset. Finally, in the last phase, the dataset with the selected features is used in a multilayer ensemble classifier framework. In addition, a classifier placement algorithm based on the Choquet integral value is designed, as the classifier placement affects the predictive performance of the ensemble framework. The proposed hybrid credit scoring model is validated on real‐world credit scoring datasets, namely, Australian, Japanese, German‐categorical, and German‐numerical datasets.     

Exploring the behaviour of base classifiers in credit scoring ensembles

Many techniques have been proposed for credit risk assessment, from statistical models to artificial intelligence methods. During the last few years, different approaches to classifier ensembles have successfully been applied to credit scoring problems, demonstrating to be more accurate than single prediction models. However, it is still a question what base classifiers should be employed in each ensemble in order to achieve the highest performance. Accordingly, the present paper evaluates the performance of seven individual prediction techniques when used as members of five different ensemble methods. The ultimate aim of this study is to suggest appropriate classifiers for each ensemble approach in the context of credit scoring. The experimental results and statistical tests show that the C4.5 decision tree constitutes the best solution for most ensemble methods, closely followed by the multilayer perceptron neural network and logistic regression, whereas the nearest neighbour and the naive Bayes classifiers appear to be significantly the worst.     

基于语言共识模型的电子商务信用风险评价方法

电子商务信用风险评价能够更好地维护市场规则并防范交易主体的合法权益.从语言评价信息的角度,利用多属性群决策方法对电子商务信用风险评价方法进行探讨.首先,提出个体语言共识测度和群体语言共识测度;然后,针对共识性水平较低的决策群体,构建一种整数规划模型,用于调整决策者给出的初始语言决策信息;最后,提出一种基于语言共识模型的电子商务信用风险评价方法,并通过电子商务信用风险评价问题说明该方法的可行性和有效性.     

Bagging and boosting negatively correlated neural networks.

In this paper, we propose two cooperative ensemble learning algorithms, i.e., NegBagg and NegBoost, for designing neural network (NN) ensembles. The proposed algorithms incrementally train different individual NNs in an ensemble using the negative correlation learning algorithm. Bagging and boosting algorithms are used in NegBagg and NegBoost, respectively, to create different training sets for different NNs in the ensemble. The idea behind using negative correlation learning in conjunction with the bagging/boosting algorithm is to facilitate interaction and cooperation among NNs during their training. Both NegBagg and NegBoost use a constructive approach to automatically determine the number of hidden neurons for NNs. NegBoost also uses the constructive approach to automatically determine the number of NNs for the ensemble. The two algorithms have been tested on a number of benchmark problems in machine learning and NNs, including Australian credit card assessment, breast cancer, diabetes, glass, heart disease, letter recognition, satellite, soybean, and waveform problems. The experimental results show that NegBagg and NegBoost require a small number of training epochs to produce compact NN ensembles with good generalization.     

神经网络的企业信用风险评估应用研究

研究企业信用风险评估准确性问题,企业存在产品质量、不良贷款等信用风险问题,企业信用风险是多种因素的综合结果,存在着不确定、非线性、随机性等特点,无法建立确定数学评估模型。只能根据专家评估指标为依据。为了提高企业信用风险评估准确率,提出一种BP神经网络的企业信用风险评估方法。先采用层次分析法构建风险评估指标体系,再用专家系统对评估指标进行量化打分,最后采用BP神经网络对企业信用风险指标进行非线性学习,并对企业信用风险等级进行评估。实验结果表明,BP神经网络的企业信用风险评估模模型能显著提高评估准确率,并能够反映企业信用风险的随机性变化特点,使评估结果更加符合实际情况,为企业信用风险评估提供了参考。     

Credit scoring for a microcredit data set using the synthetic minority oversampling technique and ensemble classifiers

Although microfinance organizations play an important role in developing economies, decision support models for microfinance credit scoring have not been sufficiently covered in the literature, particularly for microcredit enterprises. The aim of this paper is to create a three‐class model that can improve credit risk assessment in the microfinance context. The real‐world microcredit data set used in this study includes data from retail, micro, and small enterprises. To the best of the authors' knowledge, existing research on microfinance credit scoring has been limited to regression and genetic algorithms, thereby excluding novel machine learning algorithms. The aim of this research is to close this gap. The proposed models predict default events by analysing different ensemble classification methods that empower the effects of the synthetic minority oversampling technique (SMOTE) used in the preprocessing of the imbalanced microcredit data set. Initial results have shown improvement in the prediction results for certain classes when the oversampling technique with homogeneous and heterogeneous ensemble classifier methods was applied. A prediction improvement for all classes was achieved via application of SMOTE and the Consolidated Trees Construction algorithm together with Rotation Forest. To obtain a complete view of all aspects, an additional set of metrics is used in the evaluation of performance.     

Comparison of individual,ensemble and integrated ensemble machine learning methods to predict China’s SME credit risk in supply chain finance

Supply chain finance (SCF) becomes more important for small- and medium-sized enterprises (SMEs) due to global credit crunch, supply chain financing woes and tightening credit criteria for corporate lending. Currently, predicting SME credit risk is significant for guaranteeing SCF in smooth operation. In this paper, we apply six methods, i.e., one individual machine learning (IML, i.e., decision tree) method, three ensemble machine learning methods [EML, i.e., bagging, boosting, and random subspace (RS)], and two integrated ensemble machine learning methods (IEML, i.e., RS–boosting and multi-boosting), to predict SMEs credit risk in SCF and compare the effectiveness and feasibility of six methods. In the experiment, we choose the quarterly financial and non-financial data of 48 listed SMEs from Small and Medium Enterprise Board of Shenzhen Stock Exchange, six listed core enterprises (CEs) from Shanghai Stock Exchange and three listed CEs from Shenzhen Stock Exchange during the period of 2012–2013 as the empirical samples. Experimental results reveal that the IEML methods acquire better performance than IML and EML method. In particular, RS–boosting is the best method to predict SMEs credit risk among six methods.