Prediction of default payment of credit card clients using Data Mining Techniques

Subaşı, Abdülhamit; Cankurt, Selçuk

doi:10.1109/iec47844.2019.8950597

Cited by 8 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, because the dataset is imbalanced, a method is proposed to tackle the problem using synthetic minority over-sampling technique (SMOTE) [32]. Using the SMOTE method together with seven other algorithms, the random forest algorithm achieved the best performance with an accuracy of 89.01% and F1-score of 89%.…”

Section: Case Study Of Credit Card Defaulting Prediction Modelsmentioning

confidence: 99%

Artificial neural network technique for improving prediction of credit card default: A stacked sparse autoencoder approach

Ebiaredoh-Mienye

Esenogho

Swart

2021

IJECE

View full text Add to dashboard Cite

Presently, the use of a credit card has become an integral part of contemporary banking and financial system. Predicting potential credit card defaulters or debtors is a crucial business opportunity for financial institutions. For now, some machine learning methods have been applied to achieve this task. However, with the dynamic and imbalanced nature of credit card default data, it is challenging for classical machine learning algorithms to proffer robust models with optimal performance. Research has shown that the performance of machine learning algorithms can be significantly improved when provided with optimal features. In this paper, we propose an unsupervised feature learning method to improve the performance of various classifiers using a stacked sparse autoencoder (SSAE). The SSAE was optimized to achieve improved performance. The proposed SSAE learned excellent feature representations that were used to train the classifiers. The performance of the proposed approach is compared with an instance where the classifiers were trained using the raw data. Also, a comparison is made with previous scholarly works, and the proposed approach showed superior performance over other methods.

show abstract

Section: Case Study Of Credit Card Defaulting Prediction Modelsmentioning

confidence: 99%

Artificial neural network technique for improving prediction of credit card default: A stacked sparse autoencoder approach

Ebiaredoh-Mienye

Esenogho

Swart

2021

IJECE

View full text Add to dashboard Cite

show abstract

“…The public's lack of understanding of basic financial principles, as seen by the recent financial crisis, has proven that they are unable to make sound financial judgments. Individuals' minimum monthly credit card payments should be researched in depth to discover the link between consumer income, payment history, and future default payments [2]. Increasing consumer finance confidence, to avoid delinquency is a big challenge for cardholders and banks as well.…”

Section: Introductionmentioning

confidence: 99%

“…Increasing consumer finance confidence, to avoid delinquency is a big challenge for cardholders and banks as well. In a well-established financial system, risk assessment is more important than crisis management [2]. With historical financial data, for example, business financial statements, client transaction and reimbursement records, etc., we can predict business execution or individual clients' default risk and lessen the harm and instability.…”

Section: Introductionmentioning

confidence: 99%

Generalized Linear Model for Predicting the Credit Card Default Payment Risk

Li¹,

Duncan-Williams²

2022

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Predicting the credit card default is important to the bank and other lenders. The credit default risk directly affects the interest charged to the borrower and the business decision of the lenders. However, very little research about this problem used the Generalized Linear Model (GLM). In this paper, we apply the GLM to predict the risk of the credit card default payment and compare it with a decision tree, a random forest algorithm. The AUC, advantages, and disadvantages of each of the three algorithms are discussed. We explain why the GLM is a better algorithm than the other two algorithms owing to its high accuracy, easy interpretability, and implementation.

show abstract