ItemConference Paper

Integrating Explainability and Fairness in Credit Risk Prediction: A Hybrid Approach Using Tabnet, LightGBM, SHAP, and Counterfactual Explanations on the FICO Dataset

Title
Integrating Explainability and Fairness in Credit Risk Prediction: A Hybrid Approach Using Tabnet, LightGBM, SHAP, and Counterfactual Explanations on the FICO Dataset
Creator
Kapoor, Shalini; Jain, Samkit; Gupta, Praveen Kumar; Vidushi; Bhardwaj, Shashank
Description
Transparent and fair credit risk assessment is essential for responsible lending in modern financial systems. This paper presents an interpretable and ethically grounded machine learning framework for loan default prediction using the FICO Explainability Challenge dataset. We combine LightGBM, a high-performing gradient boosting model for tabular data, with TabNet, a deep learning architecture that provides intrinsic interpretability through attentive feature selection. To enhance transparency, SHapley Additive exPlanations (SHAP) are employed for global and local feature attribution, while counterfactual explanations generated using the DiCE framework offer actionable recourse. Fairness is evaluated and mitigated using IBM's AI Fairness 360 toolkit. Experimental results demonstrate that the proposed hybrid approach achieves strong predictive performance while ensuring interpretability and fairness, making it suitable for trustworthy and regulation-compliant credit risk modeling. 2026 IEEE.
Source
2026 2nd International Conference on Computing, Sciences and Communications, ICCSC 2026;
Date
01-01-2026
Publisher
Institute of Electrical and Electronics Engineers Inc.
Subject
Counterfactual Explanations; Credit Risk Prediction; Explainable AI; Fairness; LightGBM; SHAP; TabNet
Coverage
Kapoor S., Scset, Bennett University, Greater Noida, India; Jain S., Scset, Bennett University, Greater Noida, India; Gupta P.K., Scset, Bennett University, Greater Noida, India; Vidushi, Christ University, Bengaluru, India; Bhardwaj S., Kiet University, Delhi-NCR, Ghaziabad, India
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISBN: 979-833159576-0;
Format
online
Language
English
Type
Conference paper

Citation

Kapoor, Shalini; Jain, Samkit; Gupta, Praveen Kumar; Vidushi; Bhardwaj, Shashank, “Integrating Explainability and Fairness in Credit Risk Prediction: A Hybrid Approach Using Tabnet, LightGBM, SHAP, and Counterfactual Explanations on the FICO Dataset,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/25946.

Output Formats