Selecting the best bank that offered Islamic personal loan package by using consistent fuzzy preference relations (CFPR)

Kadir, Norhidayah A.; Sarudin, Ezzah Suraya; Hamid, Fairus; Shamsuddin, Nor Diyana Ahmad

doi:10.1063/1.4898512

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lucas and Xin believe that there is a correlation between loan default behavior and the use of funds by consumers, so they construct a time series model to analyze changes in consumer behavior and predict loan default risk [7]. Kadir et al integrate the prior knowledge of loan risk control experts, use Bayesian network models to establish the relationship between various factors and default behavior and explain the default mechanism [8]. Noor et al improved the random forest model by introducing weight vectors to improve the original voting decision-making mechanism, improving the prediction accuracy of the random forest model for default behavior [9].…”

Section: Related Workmentioning

confidence: 99%

A Novel Default Prediction Model Based on DNN and LightGBM

Pan,

Zhang,

et al. 2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Given the credit risk losses brought by Loan default to commercial banks, this paper, based on the America Express data set of the Kaggle platform, builds a hybrid model to predict customer default, to reduce credit risk. We first conduct data cleaning and feature engineering processing, dividing the data into category data and continuous data, and calculating the correlation between different features. We build DNN and lightGBM for credit default prediction. From the comprehensive results, the prediction effect of the mixed model is significantly better than that of the single prediction model. Among these models, our hybrid approach achieves the leading metric of 0.798. This metric is higher than XGBoost, LightGBM, and DNN by 0.013, 0.002, and 0.008 respectively.

show abstract

Section: Related Workmentioning

confidence: 99%