Madeleine-Cummings/Project-1-Data-By-Design: Project 1 Submission
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
This project develops a data-driven approach to predicting loan default risk for borrowers with limited or no credit history. Using LendingClub data, a relational dataset is constructed and analyzed through a full pipeline including data ingestion, transformation, and modeling using DuckDB and Python. The project evaluates multiple models and highlights the tradeoff between overall accuracy and the ability to detect high-risk borrowers, with a focus on improving fair and effective lending decisions.
Fields of Study & Subjects
Financial Distress and Bankruptcy Prediction
FinTech
Crowdfunding
Digital Finance
Microfinance and Financial Inclusion
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 30 March 2026
- Language
- EN