Expert Systems with Applications· 2026Q1
A fairness-aware TabTransformer framework for credit scoring with high-cardinality regional bias
- 1citations
- Q1SCImago
- 2026year
Short summary
A novel Fairness-Regularized TabTransformer model significantly outperforms XGBoost, Random Forest, and Logistic Regression in credit scoring by addressing high-cardinality regional bias.
AI-generated from the title and abstract; the full text is not read.
Key points
- A new Fairness-Regularized TabTransformer model was developed for credit scoring.
- The model specifically addresses high-cardinality regional bias.
- It outperformed XGBoost, Random Forest, and Logistic Regression baselines.
- The implementation uses R and the 'torch' library.
AI-generated from the title and abstract; the full text is not read.
Abstract
This repository contains the R source code used to generate the results, tables, and figures for the paper "A Fairness-Aware TabTransformer Framework for Credit Scoring with High-Cardinality Regional Bias" . It implements a deep learning pipeline using "torch" for R, comparing a custom Fairness-Regularized TabTransformer against industry baselines (XGBoost, Random Forest, Logistic Regression).
The authors' abstract, as published at the source. Expert Systems with Applications, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
AccountingBusiness, Management and Accounting