[논문]Machine learning models and bankruptcy prediction

Barboza, F.; Kimura, H.; Altman, E.

doi:10.1016/j.eswa.2017.04.006

Machine learning models and bankruptcy prediction

Expert systems with applications, v.83, 2017년, pp.405 - 417

Barboza, F. , Kimura, H. , Altman, E.

Abstract ▼ AI-Helper

There has been intensive research from academics and practitioners regarding models for predicting bankruptcy and default events, for credit risk management. Seminal academic research has evaluated bankruptcy using traditional statistics techniques (e.g. discriminant analysis and logistic regression) and early artificial intelligence models (e.g. artificial neural networks). In this study, we test machine learning models (support vector machines, bagging, boosting, and random forest) to predict bankruptcy one year prior to the event, and compare their performance with results from discriminant analysis, logistic regression, and neural networks. We use data from 1985 to 2013 on North American firms, integrating information from the Salomon Center database and Compustat, analysing more than 10,000 firm-year observations. The key insight of the study is a substantial improvement in prediction accuracy using machine learning techniques especially when, in addition to the original Altman's Z-score variables, we include six complementary financial indicators. Based on Carton and Hofer (2006), we use new variables, such as the operating margin, change in return-on-equity, change in price-to-book, and growth measures related to assets, sales, and number of employees, as predictive variables. Machine learning models show, on average, approximately 10% more accuracy in relation to traditional models. Comparing the best models, with all predictive variables, the machine learning technique related to random forest led to 87% accuracy, whereas logistic regression and linear discriminant analysis led to 69% and 50% accuracy, respectively, in the testing sample. We find that bagging, boosting, and random forest models outperform the others techniques, and that all prediction accuracy in the testing sample improves when the additional variables are included. Our research adds to the discussion of the continuing debate about superiority of computational methods over statistical techniques such as in Tsai, Hsu, and Yen (2014) and Yeh, Chi, and Lin (2014). In particular, for machine learning mechanisms, we do not find SVM to lead to higher accuracy rates than other models. This result contradicts outcomes from Danenas and Garsva (2015) and Cleofas-Sanchez, Garcia, Marques, and Senchez (2016), but corroborates, for instance, Wang, Ma, and Yang (2014), Liang, Lu, Tsai, and Shih (2016), and Cano et al. (2017). Our study supports the applicability of the expert systems by practitioners as in Heo and Yang (2014), Kim, Kang, and Kim (2015) and Xiao, Xiao, and Wang (2016).

주제어

참고문헌 (59)

International Review of Financial Analysis Ali 19 3 165 2010 10.1016/j.irfa.2010.03.001 Macroeconomic determinants of credit risk: Recent evidence from a cross country study

상세보기
The Journal of Finance Altman 23 4 589 1968 10.1111/j.1540-6261.1968.tb00843.x Financial ratios, discriminant analysis and the prediction of corporate bankruptcy

상세보기
Review of Accounting Studies Begley 1 4 267 1996 10.1007/BF00570833 Bankruptcy classification errors in the 1980s: An empirical analysis of Altman’s and Ohlson’s models

상세보기
Expert Systems with Applications Bernard 75 94 2017 10.1016/j.eswa.2017.01.021 Learning style identifier: Improving the precision of learning style identification through computational intelligence algorithms

상세보기
Journal of Banking & Finance Bonfim 33 2 281 2009 10.1016/j.jbankfin.2008.08.006 Credit risk drivers: Evaluating the contribution of firm level information and of macroeconomic dynamics

상세보기
Expert Systems with Applications Booth 41 8 3651 2014 10.1016/j.eswa.2013.12.009 Automated trading with performance weighted random forests and seasonality

상세보기
Machine Learning Breiman 24 2 123 1996 10.1007/BF00058655 Bagging predictors

상세보기
Machine Learning Breiman 45 1 5 2001 10.1023/A:1010933404324 Random forests
Expert Systems with Applications Calderoni 42 1 125 2015 10.1016/j.eswa.2014.07.042 Indoor localization in a hospital environment using random forest classifiers

상세보기
Expert Systems with Applications Cano 72 151 2017 10.1016/j.eswa.2016.12.008 Automatic selection of molecular descriptors using random forest: Application to drug discovery

상세보기
Carton 2006 Measuring organizational performance
Journal of Financial Markets Chen 13 2 249 2010 10.1016/j.finmar.2009.10.003 Financial distress and idiosyncratic volatility: An empirical investigation

상세보기
Journal of Banking & Finance Chen 40 211 2014 10.1016/j.jbankfin.2013.11.036 Default prediction with dynamic sectoral and macroeconomic frailties

상세보기
Applied Soft Computing Cleofas-Sánchez 44 144 2016 10.1016/j.asoc.2016.04.005 Financial distress prediction using the hybrid associative memory with translation

상세보기
Machine Learning Cortes 20 3 273 1995 10.1007/BF00994018 Support-vector networks

상세보기
Expert Systems with Applications Danenas 42 6 3194 2015 10.1016/j.eswa.2014.12.001 Selection of support vector machines based classifiers for credit risk domain

상세보기
10.1017/CBO9781316576533 Efron, B., & Hastie, T. (2016). Computer Age Statistical Inference.
Intelligent Systems in Accounting, Finance and Management Figini 23 1-2 6 2016 10.1002/isaf.1387 Corporate default prediction model averaging: A Normative linear pooling approach

상세보기
Journal of Computer and System Sciences Freund 55 1 119 1997 10.1006/jcss.1997.1504 A decision-Theoretic generalization of on-Line learning and an application to boosting

상세보기
Expert Systems with Applications Gerlein 54 193 2016 10.1016/j.eswa.2016.01.018 Evaluating machine learning classification for financial trading: An empirical approach

상세보기
The Journal of Finance Griffin 57 5 2317 2002 10.1111/1540-6261.00497 Book-to-Market equity, distress risk, and stock returns

상세보기
Evolutionary Computation Duéñez Guzmán 21 2 293 2013 10.1162/EVCO_a_00077 No free lunch and benchmarks

상세보기
Applied Soft Computing Heo 24 494 2014 10.1016/j.asoc.2014.08.009 AdaBoost based bankruptcy forecasting of Korean construction companies

상세보기
Review of Accounting Studies Hillegeist 9 1 5 2004 10.1023/B:RAST.0000013627.90884.b7 Assessing the probability of bankruptcy

상세보기
European Journal of Operational Research du Jardin 254 1 236 2016 10.1016/j.ejor.2016.03.008 A two-stage classification technique for bankruptcy prediction

상세보기
Expert Systems with Applications Kim 37 4 3373 2010 10.1016/j.eswa.2009.10.012 Ensemble with neural networks for bankruptcy prediction

상세보기
Expert Systems with Applications Kim 42 3 1074 2015 10.1016/j.eswa.2014.08.025 Geometric mean based boosting algorithm with over-sampling to resolve data imbalance problem for bankruptcy prediction

상세보기
Economic Modelling Kim 36 354 2014 10.1016/j.econmod.2013.10.005 Predicting restaurant financial distress using decision tree and adaboosted decision tree models

상세보기
Expert Systems with Applications Kruppa 40 13 5125 2013 10.1016/j.eswa.2013.03.019 Consumer credit risk: Individual probability estimates using machine learning

상세보기
Expert Systems with Applications Laha 42 10 4687 2015 10.1016/j.eswa.2015.01.030 Modeling of steelmaking process with effective machine learning techniques

상세보기
Information Sciences Li 179 1-2 89 2009 10.1016/j.ins.2008.09.003 Gaussian case-based reasoning for business failure prediction with empirical data in china

상세보기
Mathematical Problems in Engineering Li 2013 1 2013 Prediction of banking systemic risk based on support vector machine

상세보기
European Journal of Operational Research Liang 252 2 561 2016 10.1016/j.ejor.2016.01.012 Financial ratios and corporate governance indicators in bankruptcy prediction: A comprehensive study

상세보기
Expert Systems with Applications López Iturriaga 42 6 2857 2015 10.1016/j.eswa.2014.11.025 Bankruptcy visualization and prediction using neural networks: A study of u.s. commercial banks

상세보기
Expert Systems with Applications Mahmoudi 42 5 2510 2015 10.1016/j.eswa.2014.10.037 Detecting credit card fraud by modified fisher discriminant analysis

상세보기
Expert Systems with Applications Maione 49 60 2016 10.1016/j.eswa.2015.11.024 Comparative study of data mining techniques for the authentication of organic grape juice based on ICP-MS analysis

상세보기
Expert Systems with Applications de Menezes 69 62 2017 10.1016/j.eswa.2016.08.014 Data classification with binary response through the boosting algorithm and logistic regression

상세보기
Expert Systems with Applications Min 28 4 603 2005 10.1016/j.eswa.2004.12.008 Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters

상세보기
Expert Systems with Applications Nanni 36 2 3028 2009 10.1016/j.eswa.2008.01.018 An experimental comparison of ensemble of classifiers for bankruptcy prediction and credit scoring

상세보기
Nature Biotechnology Noble 24 12 1565 2006 10.1038/nbt1206-1565 What is a support vector machine?

상세보기
Journal of Accounting Research Ohlson 18 1 109 1980 10.2307/2490395 Financial ratios and the probabilistic prediction of bankruptcy

상세보기
IEEE Transactions on Biomedical Engineering Oskoei 55 8 1956 2008 10.1109/TBME.2008.919734 Support vector machine-Based classification scheme for myoelectric control applied to upper limb

상세보기
Osuna 130 1997 Computer vision and pattern recognition, 1997. proceedings., 1997 ieee computer society conference on Training support vector machines: An application to face detection
Expert Systems with Applications Pal 49 48 2016 10.1016/j.eswa.2015.11.027 Business health characterization: A hybrid regression and support vector machine analysis

상세보기
Expert Systems with Applications Park 41 11 5227 2014 10.1016/j.eswa.2014.01.032 Parametric models and non-parametric machine learning models for predicting option prices: Empirical comparison study over KOSPI 200 index options

상세보기
Expert Systems with Applications Subasi 37 12 8659 2010 10.1016/j.eswa.2010.06.065 EEG signal classification using PCA, ICA, LDA and support vector machines

상세보기
Technological and Economic Development of Economy Tian 18 1 5 2012 10.3846/20294913.2012.661205 Recent advances on support vector machines research

상세보기
Rev Quant Finan Acc Trustorff 36 4 565 2010 10.1007/s11156-010-0190-3 Credit risk prediction using support vector machines

상세보기
Applied Soft Computing Tsai 24 977 2014 10.1016/j.asoc.2014.08.047 A comparative study of classifier ensembles for bankruptcy prediction

상세보기
International Journal of Contemporary Hospitality Management Upneja 13 2 54 2001 10.1108/09596110110381825 An examination of capital structure in the restaurant industry

상세보기
Expert Systems with Applications Wang 38 1 223 2011 10.1016/j.eswa.2010.06.048 A comparative assessment of ensemble learning for credit scoring

상세보기
Knowledge-Based Systems Wang 26 61 2012 10.1016/j.knosys.2011.06.020 Two credit scoring models based on dual strategy ensemble trees

상세보기
Expert Systems with Applications Wang 41 5 2353 2014 10.1016/j.eswa.2013.09.033 An improved boosting based on feature selection for corporate bankruptcy prediction

상세보기
Applied Soft Computing Xiao 43 73 2016 10.1016/j.asoc.2016.02.022 Ensemble classification based on supervised clustering for credit scoring

상세보기
Information Sciences Yeh 254 98 2014 10.1016/j.ins.2013.07.011 Going-concern prediction using hybrid random forests and rough set approach

상세보기
Expert Systems with Applications Yu 37 2 1351 2010 10.1016/j.eswa.2009.06.083 Support vector machine based multiagent ensemble learning for credit risk evaluation

상세보기
Procedia - Social and Behavioral Sciences Yurdakul 109 784 2014 10.1016/j.sbspro.2013.12.544 Macroeconomic modelling of credit risk for banks

상세보기
Expert Systems with Applications Zhao in press 2014 Investigation and improvement of multi-layer perception neural networks for credit scoring
International Journal of Systems Science Zhou 45 3 241 2014 10.1080/00207721.2012.720293 Bankruptcy prediction using SVM models with a new approach to combine features selection and parameter optimisation

상세보기

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증

Machine learning models and bankruptcy prediction

Abstract ▼ AI-Helper

주제어

참고문헌 (59)

이 논문을 인용한 문헌

관련 콘텐츠

원문 URL 링크

연관된 기능

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트