Credit Risk Scoring with Bayesian Network Models

Leong, Chee Kian

doi:10.1007/s10614-015-9505-8

Cited by 58 publications

(33 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Cuicui Luo et al [6] comparing deep learning algorithms such as belief network and restricted Boltzmann machine with popular machine learning algorithms such as logistic regression, support vector machine and multi-layer perceptron, we find that DBN performs best in area evaluation performance using classification accuracy and receiver performance curve. CK Leong et al [7] proposed a Bayesian network model to solve the problems of truncated samples, sample imbalance and real-time implementation in credit risk scoring. Compared with the competition model (logical regression and neural network), it performs better in accuracy, sensitivity and other dimensions.…”

Section: A Selecting a Templatementioning

confidence: 99%

Mobile User Credit Prediction Based on LightGBM

Guo¹,

Zhu²,

Pei³

et al. 2019

Proceedings of the 2019 International Conference on Big Data, Electronics and Communication Engineering (BDECE 2019)

View full text Add to dashboard Cite

LightGBM algorithm is used to build an effective credit score prediction model for mobile users and improve the prediction system of personal credit score. Firstly, linear correlation is analyzed to build feature set, then k-means algorithm is used to analyze feature set clustering, and finally, credit scoring model is built by LightGBM. Experiments on real data provided by the digital China innovation competition show that this method has higher accuracy than GBDT, XGBoost and other algorithms. By clustering the data feature set based on linear correlation analysis and applying it to LightGBM credit scoring model, mobile users' credit scores can be predicted more accurately.

show abstract

Section: A Selecting a Templatementioning

confidence: 99%

Mobile User Credit Prediction Based on LightGBM

Guo¹,

Zhu²,

Pei³

et al. 2019

Proceedings of the 2019 International Conference on Big Data, Electronics and Communication Engineering (BDECE 2019)

View full text Add to dashboard Cite

show abstract

“…Bayesian network model performs better than logistic regression and neural network models if we look at the accuracy, sensitivity, precision and the receiver characteristic curve. 30 Neuro-fuzzy systems were also used as a model for credit score classification. Fang 31 and Piramuthu 32 used neuro-fuzzy systems and neural networks, where ANFIS proved to be more accurate.…”

Section: Literature Reviewmentioning

confidence: 99%

A Fuzzy Inference System for Credit Scoring using Boolean Consistent Fuzzy Logic

Latinović¹,

Dragović²,

Arsić³

et al. 2018

IJCIS

View full text Add to dashboard Cite

This study proposes implementation of Boolean consistent fuzzy inference system for credit scoring purposes. Fuzzy inference system (FIS) allows domain experts to express their knowledge in the form of fuzzy rules, which enables combination of automatic rating with human judgment. Crucial for this model is that fuzzy rules are being evaluated using Boolean consistent fuzzy logic, which preserves all Boolean axioms. Experimental results show that the Boolean consistent FIS outperforms the conventional FIS in terms of classification accuracy, precision, and recall. Consistent fuzzy logic could contribute to the rightful approval of more loans which in turn would have positive effects on economic growth.

show abstract

“…The database provided by the credit bureau has 10,356 customer observations of direct retail consumer credit operations and 198 variables for the year 2014. Although random trees and BART were designed for larger datasets it is not unusual to find papers that aim to compare estimation methods designed for big datasets with sample sizes equivalent to ours, see, for instance, Chipman et al (2010), Yeh et al (2012), Leong (2016), Abellán & Castellano (2017), Bequé & Lessmann (2017), and several papers analysed in Lessmann et al (2015) review.…”

Section: Databasementioning

confidence: 99%

Application of bayesian additive regression trees in the development of credit scoring models in Brazil

Filho

Artes

2018

Prod.

View full text Add to dashboard Cite

Paper aims: This paper presents a comparison of the performances of the Bayesian additive regression trees (BART), Random Forest (RF) and the logistic regression model (LRM) for the development of credit scoring models. Originality:It is not usual the use of BART methodology for the analysis of credit scoring data. The database was provided by Serasa-Experian with information regarding direct retail consumer credit operations. The use of credit bureau variables is not usual in academic papers.Research method: Several models were adjusted and their performances were compared by using regular methods. Main findings:The analysis confirms the superiority of the BART model over the LRM for the analyzed data. RF was superior to LRM only for the balanced sample. The best-adjusted BART model was superior to RF. Implications for theory and practice:The paper suggests that the use of BART or RF may bring better results for credit scoring modelling. KeywordsCredit. Machine learning. Logistic regression. BART. Random Forest.

show abstract

Credit Risk Scoring with Bayesian Network Models

Cited by 58 publications

References 16 publications

Mobile User Credit Prediction Based on LightGBM

Mobile User Credit Prediction Based on LightGBM

A Fuzzy Inference System for Credit Scoring using Boolean Consistent Fuzzy Logic

Application of bayesian additive regression trees in the development of credit scoring models in Brazil

Contact Info

Product

Resources

About