Using semi-supervised classifiers for credit scoring

Kennedy, Kenneth; Namee, Brian Mac; Delany, Sarah Jane

doi:10.1057/jors.2011.30

Cited by 36 publications

(22 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Particularly, with the development of new predictive modelling techniques in machine learning and the statistical literature, various studies have assessed how these newer approaches perform compared to more established methods with regards to scoring unsecured consumer loans such as personal loans and credit cards (Baesens et al, 2003;Kennedy et al, 2013b;Lessmann et al, 2015). However, when it comes to 15 secured lending, research findings regarding credit risk assessment of mortgage loans are much more scarce, despite the fact that they are among the largest class of assets on European banks' balance sheets.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

“…default or no default) have led to a variety of applications in credit risk. Previous reviews of various modelling approaches and empirical evaluations have been carried out by Baesens et al (2003), Crook et al (2007), Crook and Bellotti (2009), Brown and Mues (2012), Kennedy et al (2013b), and Lessmann et al (2015). Some of their results suggest that newer approaches such as ensemble classifiers offer some improvement 50 in predictive ability over logistic regression which could prove valuable for managing credit risk.…”

Section: Research Question; Choice Of Techniquesmentioning

confidence: 99%

“…The impact that such imbalanced datasets have on the quality of the resulting models was studied by Burez andVan den Poel (2009), Brown andMues (2012), and Kennedy et al (2013b). Both Kennedy et al (2013b) and Brown and Mues (2012) found that…”

Section: Related Literature and Main Contributionsmentioning

confidence: 99%

“…Logistic Regression (LR) is known as a classifier that performs reasonably well across many application settings and data types, including credit scoring (Brown and Mues, 2012;Kennedy et al, 2013b;Lessmann et al, 2015). To avoid the problems associated with stepwise regression, and to make the model comparison as fair as possible, Regularised Logistic Regression (RLR) is …”

Section: Logistic Regressionmentioning

confidence: 99%

See 3 more Smart Citations

An empirical comparison of classification algorithms for mortgage default prediction: evidence from a distressed mortgage market

Fitzpatrick

Mues

2016

European Journal of Operational Research

View full text Add to dashboard Cite

Highlights• We evaluate default prediction performance of machine learning/regression models.• Including boosted trees, random forests, penalised linear/semi-parametric logistic regression.• Using data on over 300,000 residential mortgage loans.• The results indicate varying degrees of predictive power.• Statistical tests suggest boosted regression trees outperform penalised logistic regression.

show abstract

Section: Accepted Manuscriptmentioning

confidence: 99%

Section: Research Question; Choice Of Techniquesmentioning

confidence: 99%

Section: Related Literature and Main Contributionsmentioning

confidence: 99%

Section: Logistic Regressionmentioning

confidence: 99%

See 2 more Smart Citations

An empirical comparison of classification algorithms for mortgage default prediction: evidence from a distressed mortgage market

Fitzpatrick

Mues

2016

European Journal of Operational Research

View full text Add to dashboard Cite

show abstract

“…A másik megközelítés ragaszkodik a reprezentatív minta alkalmazásához, és a csődös vállalatok adatainak nagyobb súlyt adva oldják meg azt a problémát, hogy az adatbányászati módszerek hajlamosak a többségi csoport sajátosságaira specializálódni. Ezen a területen Kennedy et al [2013] folytatott kutatásokat.…”

Section: A Minta Felosztása a Két Csoport Közöttunclassified

Dinamikus pénzügyi mutatószámok alkalmazása a csődelőrejelzésben

Nyitrai¹

View full text Add to dashboard Cite

Generalized fuzzy soft sets theory‐based novel hybrid ensemble credit scoring model

Zhang

Feng

2018

Int. J Fin Econ

View full text Add to dashboard Cite

In banking and peer‐to‐peer loan applicant firms, customer credit scores have numerous applications in risk control and precision marketing. Numerous credit scoring techniques act as classification methods. In this paper, the main issue is simultaneous and hybrid utilization of the feature selection (FS) algorithm and ensemble learning classification algorithms with respect to their parameter settings to achieve higher performance in the proposed credit scoring model. As a result, this paper reports a hybrid data mining model of generalized fuzzy soft sets (GFSS) theory‐based ensemble learning classification algorithms based on three stages. The first stage addresses data gathering and preprocessing. The second stage uses the adaptive elastic net‐based FS algorithm to eliminate irrelevant or weakly correlated variables. After the appropriate variables are chosen, they are applied to the proposed ensemble model. In the third stage, GFSS theory is exploited to construct a novel weight assignment mechanism for each individual credit scoring model in the ensemble model according to performance. Several comparisons are conducted to validate the proposed model using real world credit datasets. The experimental results, analysis, and statistical tests prove the ability of the proposed approach to improve classification performance against all of the base classifier, hybrid, and combination methods in terms of average accuracy, area under the curve, H‐measure, and Brier score.

show abstract

Using semi-supervised classifiers for credit scoring

Cited by 36 publications

References 57 publications

An empirical comparison of classification algorithms for mortgage default prediction: evidence from a distressed mortgage market

An empirical comparison of classification algorithms for mortgage default prediction: evidence from a distressed mortgage market

Dinamikus pénzügyi mutatószámok alkalmazása a csődelőrejelzésben

Generalized fuzzy soft sets theory‐based novel hybrid ensemble credit scoring model

Contact Info

Product

Resources

About