Hyper Personalized Risk Assessment for Fintech Using GEN AI

Read full text Summarise with VIRAT
Authors: B. Vijayakumar, D. Prasanaa Venkatesh, V. Sailesh, A. Ariharan
Cited by: 0
References: 15

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Traditional credit risk assessment models often underperform when applied to real-world data from medium and micro enterprises (MMEs), primarily due to data imbalance, noisy financial records, and limited historical credit information [7,12].In this study, we propose a deep learning-based framework for credit risk prediction that employs a stacked ensemble approach integrating Random Forest, Logistic Regression, and Convolutional Neural Network (CNN) as base learners, and a Multi-Layer Perceptron (MLP) is used as the meta-learner to merge and refine their predictions [1,5].The model adopts a hybrid resampling strategy, combining SMOTE with Edited Nearest Neighbours (SMOTE-ENN) to balance uneven class distributions and reduce bias in credit risk datasets [1].The financial feature set is designed to reflect time-dependent trends and borrower behavioral patterns [5,7].The ensemble system is trained and validated on benchmark datasets as well as real-world SME financial records, achieving improved sensitivity and precision in identifying high-risk borrowers [1,5].This robust and scalable solution strengthens credit screening, helping lenders and financial institutions reduce defaults and enhance decision-making for underserved enterprise segments [11,12].

Fields of Study & Subjects

Financial Distress and Bankruptcy Prediction Imbalanced Data Classification Techniques FinTech Crowdfunding Digital Finance

Publication details

Journal / source
Advances in intelligent systems research/Advances in Intelligent Systems Research
Pages
732–742
Publication date
1 April 2026
Language
EN
Document type
Book chapter