Features selection,data mining and finacial risk classification: a comparative study

The aim of this paper is to compare several predictive models that combine features selection techniques with data mining classifiers in the context of credit risk assessment in terms of accuracy, sensitivity and specificity statistics. The t‐statistic, Battacharrayia statistic, the area between the receiver operating characteristic, Wilcoxon statistic, relative entropy, and genetic algorithms were used for the features selection task. The selected features are used to train the support vector machine (SVM) classifier, backpropagation neural network, radial basis function neural network, linear discriminant analysis and naive Bayes classifier. Results from three datasets using a 10‐fold cross‐validation technique showed that the SVM provides the best accuracy under all features selections techniques adopted in the study for all three datasets. Therefore, the SVM is an attractive classifier to be used in real applications for bankruptcy prediction in corporate finance and financial risk management in financial institutions. In addition, we found that our best results are superior to earlier studies on the same datasets.     

Evaluating business credit risk by means of approach‐integrating decision rules and case‐based learning

This research utilizes a new approach which uses a hybrid learning system that combines two representations of knowledge: the first in a form of decision rules referring to general knowledge, and the other of single cases corresponding to exceptions or untypical situations. The Explore algorithm was chosen as a tool for inducing general rules. It generates all simple and sufficiently strong general rules from a given data set. Examples discovered by these rules are then used to identify exceptions and untypical cases. The paper discusses problems connected with tuning parameters of this approach and introduces a new procedure for this task. This methodology is applied to solve the problem of evaluating the risk of business credit applications in a Polish commercial bank. Using information about business credit applications, as described by 35 economic parameters and using five groups of banking risk, a knowledge base consisting of 70 decision rules and 15 specific cases was induced. Testing this model in the standard ‘leaving‐one‐out’ way we achieved the best classification accuracy of 81%. A comparative study showed that results obtained by other machine‐learning algorithms resulted in significantly worse classification accuracy. Copyright © 2001 John Wiley & Sons, Ltd.     

债券信用溢价的共同因子与结构变化:基于机器学习方法

共同因子是刻画风险溢价的重要基础,将共同因子模型应用于公司债券市场有助于合理估计信用风险溢价.本文利用机器学习算法探究债券信用溢价因子的存在性以及结构变化后发现:规模、下行风险、价值、波动率以及流动性等五个公司债券共同因子对单个债券信用溢价有较好的解释能力,动量因子对信用溢价的解释能力较差,流动性因子具有较强的逆周期防...     

Towards an early warning system for sovereign defaults leveraging on machine learning methodologies

In this study, we address the topic of credit risk stemming from central governments from a technical point of view. First, we explore various econometric and machine learning techniques to build an enhanced sovereign rating system that effectively differentiates the risk of default among countries. Our empirical results indicate that the machine learning method of XGBOOST has a superior out-of-sample and out-of-time predictive performance. Then, we use the models developed to calibrate a sovereign rating system and provide useful insights into the set-up of a parsimonious early warning system. Our results provide a more concise view of the most robust method for classifying countries’ default risk with significant regulatory implications, given that the efficient assessment of sovereign debt is crucial for effective proactive risk measurement.     

Enhancing the government accounting information systems using social media information: An application of text mining and machine learning

This study demonstrates a way of bringing an innovative data source, social media information, to the government accounting information systems to support accountability to stakeholders and managerial decision-making. Future accounting and auditing processes will heavily rely on multiple forms of exogenous data. As an example of the techniques that could be used to generate this needed information, the study applies text mining techniques and machine learning algorithms to Twitter data. The information is developed as an alternative performance measure for NYC street cleanliness. It utilizes Naïve Bayes, Random Forest, and XGBoost to classify the tweets, illustrates how to use the sampling method to solve the imbalanced class distribution issue, and uses VADER sentiment to derive the public opinion about street cleanliness. This study also extends the research to another social media platform, Facebook, and finds that the incremental value is different between the two social media platforms. This data can then be linked to government accounting information systems to evaluate costs and provide a better understanding of the efficiency and effectiveness of operations.     

Applying machine learning algorithms to predict default probability in the online credit market: Evidence from China

Using data from Renrendai and three machine learning algorithms, namely, k-nearest neighbor, support vector machine, and random forest, we predicted the default probability of online loan borrowers and compared their prediction performance with that of a logistic model. The results show that, first, based on the AUC (area under the ROC curve) value, accuracy rate and Brier score, the machine learning models can accurately predict the default risk of online borrowers. Second, the integrated discrimination improvement (IDI) test results show that the prediction performance of the machine learning algorithms is significantly better than that of the logistic model. Third, after constructing the investor profit function with misclassification cost, we find that the machine learning algorithms can provide more benefits to investors.     

Integrating machine learning and workflow management to support acquisition and adaptation of workflow models

Current workflow management systems (WFMS) offer little aid for the acquisition of workflow models and their adaptation to changing requirements. To support these activities we propose to apply techniques from machine learning, which enable an inductive approach to workflow acquisition and adaptation. We present a machine learning component that combines two different machine learning algorithms: the first induces the structure of sequential workflows and the second is responsible for the induction of transition conditions. The second task can be solved by applying standard decision rule induction algorithms. In this contribution we focus mainly on the algorithms for the first task. For this purpose we describe two algorithms based on the induction of hidden Markov models. The first algorithm is a bottom‐up, specific‐to‐general algorithm and the other applies a top‐down, general‐to‐specific strategy. Both algorithms have been implemented in a research prototype. In six scenarios we evaluate and compare the two algorithms experimentally. The induced workflow models can be imported by the business process management system ADONIS. Copyright © 2000 John Wiley & Sons, Ltd.     

Predicting credit card delinquencies: An application of deep neural networks

The objective of this paper is twofold. First, it develops a prediction system to help the credit card issuer model the credit card delinquency risk. Second, it seeks to explore the potential of deep learning (also called a deep neural network), an emerging artificial intelligence technology, in the credit risk domain. With real-life credit card data linked to 711,397 credit card holders from a large bank in Brazil, this study develops a deep neural network to evaluate the risk of credit card delinquency based on the client's personal characteristics and the spending behaviours. Compared with machine-learning algorithms of logistic regression, naive Bayes, traditional artificial neural networks, and decision trees, deep neural networks have a better overall predictive performance with the highest F scores and area under the receiver operating characteristic curve. The successful application of deep learning implies that artificial intelligence has great potential to support and automate credit risk assessment for financial institutions and credit bureaus.     

Discovering probabilistic decision rules

Techniques to generate probabilistic decision rules are presented that are used to forecast or measure the competitiveness of companies. Rules estimating the competitiveness of companies are described and the generated rules are then applied to forecast the competitiveness of previously unseen companies. Experimental results show that probabilistic decision rule technique outperforms many other machine learning and statistical techniques in this application domain. These findings are further confirmed in a second application, the classification of credits into either good or bad. © 1997 John Wiley & Sons, Ltd.     

Predicting SME loan delinquencies during recession using accounting data and SME characteristics: The case of Greece

The objective of this paper is the comparison of various credit‐scoring models (i.e. binomial logistic regression, decision tree, multilayer perceptron neural network, radial basis function, and support vector machine) in evaluating the risk of small and micro enterprises' (SMEs') loan delinquencies based on accounting data and applicants' specific attributes. Exploiting a representative large data set of SMEs' loans granted by a large Greek commercial bank in the expansion period, we track the evolution of SMEs' delinquencies over the recession period August 2010 to July 2012. This time frame encompasses a period of manageable levels of delays (early recession period: August 2011–July 2012) and a period when delays were increased to a very high degree (deep recession period: August 2011–July 2012). Comparison of the employed credit‐scoring models during the early recession period shows that the multilayer perceptron neural network produces the highest predicting capacity, followed by the support vector machine model. As the crisis deepens, the support vector machine model presents the highest predicting accuracy, followed by the decision tree and then the multilayer perceptron model. Generally, the predictive performance of all credit‐scoring models seems to be substantially reduced as the recession escalates. Our paper has important implications for the proper financing of SMEs given their importance for the European economy.     

A real options approach for evaluating the implementation of a risk-sensitive capital rule in banks

I evaluate a bank's incentives to implement a risk-sensitive regulatory capital rule. The decision making is analyzed within a real options framework where optimal policies are derived in terms of threshold levels of credit risk. I provide a numerical example for the implementation of internal ratings based models for credit risk (the IRB approach) under the new Basel Accord (Basel II).     

When to Lean against the Wind

In this paper, we show that policymakers can distinguish between good and bad credit booms with high accuracy and they can do so in real time. Evidence from 17 countries over nearly 150 years of modern financial history shows that credit booms that are accompanied by house price booms and a rising loan‐to‐deposit ratio are much more likely to end in a systemic banking crisis than other credit booms. We evaluate the predictive accuracy for different classification models and show that characteristics observed in real time contain valuable information for sorting the data into good and bad booms.     

Interpretable selective learning in credit risk

Forecasting credit default risk has been an important research field for several decades. Traditionally, logistic regression has been widely recognized as a solution because of its accuracy and interpretability. Although complex machine learning models may improve accuracy over simple logistic regressions, their interpretability has prevented their use in credit risk assessment. We introduce a neural network with a selective option to increase interpretability by distinguishing whether linear models can explain the dataset. Our methods are tested on two datasets: 25,000 samples from the Taiwan payment system collected in October 2005 and 250,000 samples from the 2011 Kaggle competition. We find that, for most of samples, logistic regression will be sufficient, with reasonable accuracy; meanwhile, for some specific data portions, a shallow neural network model leads to much better accuracy without significantly sacrificing interpretability.     

Corporate governance performance ratings with machine learning

We use machine learning with a cross-sectional research design to predict governance controversies and to develop a measure of the governance component of the environmental, social, governance (ESG) metrics. Based on comprehensive governance data from 2,517 companies over a period of 10 years and investigating nine machine-learning algorithms, we find that governance controversies can be predicted with high predictive performance. Our proposed governance rating methodology has two unique advantages compared with traditional ESG ratings: it rates companies' compliance with governance responsibilities and it has predictive validity. Our study demonstrates a solution to what is likely the greatest challenge for the finance industry today: how to assess a company's sustainability with validity and accuracy. Prior to this study, the ESG rating industry and the literature have not provided evidence that widely adopted governance ratings are valid. This study describes the only methodology for developing governance performance ratings based on companies' compliance with governance responsibilities and for which there is evidence of predictive validity.     

基于数据挖掘的持卡人信用风险管理研究

目前的信用卡信用风险研究主要是如何提高模型的预测准确率。针对银行信用卡数据的异质性和信用数据的高度非线性,本文提出了对持卡人信用风险管理的混合数据挖掘方法。该方法包含两个阶段,在聚类阶段,样本数据被聚成同质的类,删除孤立点,不一致样本点重置标签,使样本更具有代表性;在分类阶段,基于样本进行训练生成支持向量机分类器法,对待分样本分类。基于实际数据进行了数值实验,并根据各类样本的特点提出了相应的风险管理策略。     

个人信用评分关键技术研究的新进展

从系统论的角度总结了个人信用评分发展的前沿问题,从数据预处理、指标体系筛选、以及模型设计三个方面对个人信用评分关键技术的最新研究成果进行了细致分类和综合比较,从而指出个人信用评分研究中存在的难点以及未来发展方向。     

A Comparative Analysis of Inductive-Learning Algorithms

Recently there has been an increasing interest in applying inductive learning algorithms to generate rules/patterns from a given example set. While such approaches serve as an efficient way of resolving the knowledge-acquisition bottleneck, their predictive accuracy, which is the popular measure of performance, varies widely. This paper contrasts major inductive-learning algorithms and examines their performance with two performance measures: the predictive accuracy and the representation language. Experiments involved three inductive-learning algorithms and five different managerial tasks in construction project assessment and bankruptcy-prediction domains. The test results indicate that the model performance is dependent on tasks with an exception of the neural network model and that there is a an effect of group proportion in the example set used to construct the model. The neural network approach presents relatively stable predictive power across different task domains, although it is difficult to interpret its representation.     

A comparison of machine‐learning classifiers for selecting money managers

Machine‐learning algorithms have performed well on noisy datasets that are typical of financial data. This paper compares the performance of three types of machine‐learning classifier for selecting money managers. Naïve Bayes, neural network and decision tree learners were applied to a dataset of US equity managers. Although other studies have suggested that the performance of classifiers appears to be highly dependent on the nature of the problem and the dataset, the learning algorithms each had similar predictive accuracy and all outperformed by a substantial margin simple manager selection rules that are typical of the ways in which money managers and mutual funds are selected by investors. The results indicate that machine learners can be used as a decision‐support aid to improve the selection of money managers. Copyright © 2005 John Wiley & Sons, Ltd.     

Can machine learning approaches predict corporate bankruptcy? Evidence from a qualitative experimental design

Bankruptcy prediction has received a growing interest in corporate finance and risk management recently. Although numerous studies in the literature have dealt with various statistical and artificial intelligence classifiers, their performance in credit risk forecasting needs to be further scrutinized compared to other methods. In the spirit of Chen, Härdle and Moro (2011, Quantitative Finance), we design an empirical study to assess the effectiveness of various machine learning topologies trained with big data approaches and qualitative, rather than quantitative, information as input variables. The experimental results from a ten-fold cross-validation methodology demonstrate that a generalized regression neural topology yields an accuracy measurement of 99.96%, a sensitivity measure of 99.91% and specificity of 100%. Indeed, this specific model outperformed multi-layer back-propagation networks, probabilistic neural networks, radial basis functions and regression trees, as well as other advanced classifiers. The utilization of advanced nonlinear classifiers based on big data methodologies and machine learning training generates outperforming results compared to traditional methods for bankruptcy forecasting and risk measurement.     

A firefly algorithm modified support vector machine for the credit risk assessment of supply chain finance

PurposeNowadays, Supply Chain Finance (SCF) has been developing rapidly since the emergence of credit risk. Therefore, this paper used SVM optimized by the firefly algorithm, which is called firefly algorithm support vector machine (FA-SVM), and applied it to SCF evaluation with a different indicator selection.Design/methodology/approachIn this paper, we used FA-SVM to assess the credit risk of supply chain finance with extracted index through correlation and appraisal analysis, and finally determined 3 first-level indicators and 15 third-level indicators. Through the application analysis, 39 SMEs (117 sample data) were selected from the Computer and Electronic Communications Manufacturing Industry as the characteristics for the input variables, to verify the improvement effect of the method relative to the LIBSVM and the classification pretest effect in the credit risk assessment of the SCF.FindingsThe results showed that FA-SVM could improve the accuracy of classification prediction compared with LIBSVM, and decrease the error rate of falseness recognize credible enterprise to untrusted enterprise.Originality/valueThis paper appliedthe firefly support vector machine in the supply chain financial evaluation for the first time. The output variable was described in a more detailed manner during the index define, and the random selection set in the process of FA-SVM data training.