Transforming financial documents into credit decisions using explainable artificial intelligence and optical character recognition
Sachin Malave, Bharti Khemani, Hrishit Patil, Sanket Nandurkar, Om Nandurkar, Ayush Nayak · 2026
Read Transforming financial documents into credit decisions using explainable artificial intelligence and optical character recognition by Sachin Malave, Bharti Khemani, Hrishit Patil, Sanket Nandurkar, Om Nandurkar, Ayush Nayak (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13224371.txt.
Description
Sachin Malave and co-authors build, in 2026, a credit decision system that reads documents and explains its calls. Banks increasingly use machine learning for lending, but opaque models raise fairness and trust concerns. Their pipeline first extracts data from applicant documents with text recognition tools, then cleans and structures it.
Several models were trained on those features, and a gradient boosting model scored highest at over ninety-two percent accuracy. Two explanation tools show which factors drive each decision, globally and case by case. The authors argue that pairing document reading with explainable models can satisfy regulators and borrowers while keeping accuracy high.
Catalog record
| CREATOR | Sachin Malave, Bharti Khemani, Hrishit Patil, Sanket Nandurkar, Om Nandurkar, Ayush Nayak |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |