paper-with-me

홈 › Papers

Assessment of creditworthiness models privacy-preserving training with synthetic data

2022-12-31 · Ricardo Muñoz-Cancino, Cristián Bravo, Sebastián A. Ríos, Manuel Graña

Credit scoring models are the primary instrument used by financial institutions to manage credit risk. The scarcity of research on behavioral scoring is due to the difficult data access. Financial institutions have to maintain the privacy and security of borrowers' information refrain them from collaborating in research initiatives. In this work, we present a methodology that allows us to evaluate the performance of models trained with synthetic data when they are applied to real-world data. Our results show that synthetic data quality is increasingly poor when the number of attributes increases. However, creditworthiness assessment models trained with synthetic data show a reduction of 3\% of AUC and 6\% of KS when compared with models trained with real data. These results have a significant impact since they encourage credit risk investigation from synthetic data, making it possible to maintain borrowers' privacy and to address problems that until now have been hampered by the availability of information.

📄 PDF Abstract BibTeX arXiv:2301.01212

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy Preserving

Similar Papers 제목 키워드 기반

Privacy-Preserving Credit Risk Prediction with Alternative Data

2026-06-09 · Hongzhe Zhang, Jiarong Xu, Jing He, Xiao Fang arxiv

Credit risk prediction is a critical problem in the consumer credit industry. Traditionally, financial institutions construct credit risk prediction models using borrowers' demographic, financial, and credit history data…

Computational Efficiency

Learning Latent Representations of Bank Customers With The Variational Autoencoder

2019-03-14 · Rogelio A. Mancisidor, Michael Kampffmeyer, Kjersti Aas, Robert Jenssen

Learning data representations that reflect the customers' creditworthiness can improve marketing campaigns, customer relationship management, data and process management or the credit risk assessment in retail banks. In …

ClusteringManagementMarketing

Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable Stress Detection

2024-01-24 · Lucas Lange, Nils Wenzlitschke, Erhard Rahm

Smartwatch health sensor data are increasingly utilized in smart health applications and patient monitoring, including stress detection. However, such medical data often comprise sensitive personal information and are re…

Privacy Preserving

Privacy-Preserving Synthetic Review Generation with Diverse Writing Styles Using LLMs

2025-07-24 · Tevin Atwal, Chan Nam Tieu, Yefeng Yuan, Zhan Shi 외 arxiv

The increasing use of synthetic data generated by Large Language Models (LLMs) presents both opportunities and challenges in data-driven applications. While synthetic data provides a cost-effective, scalable alternative …

Towards Privacy-Preserving Mental Health Support with Large Language Models

2026-01-05 · Dong Xue, Jicheng Tu, Ming Wang, Xin Yan 외 arxiv

Large language models (LLMs) have shown promise for mental health support, yet training such models is constrained by the scarcity and sensitivity of real counseling dialogues. In this article, we present MindChat, a pri…

Federated Learning