Credit risk analysis with classification Restricted Boltzmann Machine

Bayraktar, Mustafa; Aktaş, Mehmet S.; Kalipsiz, Oya; Susuz, Orkun; Bayracı, Selçuk

doi:10.1109/siu.2018.8404397

Cited by 8 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They conclude that NB fulfills of needs of bankers [14]. Bayraktar et al compared commonly used machine learning methods with deep learning methods (Classification Restricted Boltzmann Machine and Multilayer Artificial Neural Networks) [15]. Aphale and Shinde used various ML techniques (Neural Network, Discriminant Analysis, Naïve Bayes, K-Nearest Neighbor, Linear Regression, Ensemble Learning, and Decision Tress) to predict the creditworthiness of borrowers [3].…”

Section: August 2022mentioning

confidence: 99%

Predicting acceptance of the bank loan offers by using support vector machines

AKÇA

Sevli

2022

International Advanced Researches and Engineering Journal

View full text Add to dashboard Cite

Loans are one of the main profit sources in banking system. Banks try to select reliable customers and offer them personal loans, but customers can sometimes reject bank loan offers. Prediction of this problem is an extra work for banks, but if they can predict which customers will accept personal loan offers, they can make a better profit. Therefore, at this point, the aim of this study is to predict acceptance of the bank loan offers using the Support Vector Machine (SVM) algorithm. In this context, SVM was used to predict results with four kernels of SVM, with a grid search algorithm for better prediction and cross validation for much more reliable results. Research findings show that the best results were obtained with a poly kernel as 97.2% accuracy and the lowest success rate with a sigmoid kernel as 83.3% accuracy. Some precision and recall values are lower than normal ones, like 0.108 and 0.008 due to unbalanced dataset, like for 1 true value, there are 9 negative values (9.6% true value). This study recommends the use of SVC in banking system while predicting acceptance of bank loan offers.

show abstract

Section: August 2022mentioning

confidence: 99%