Phase 2 (From Research to Industrialization): Application of Transformer Models to Raw Credit Bureau Files for Improved Credit Risk Modelling Performance

We are developing a new system to help banks and financial institutions better assess credit risk—the chance that a borrower might not repay a loan. Traditional methods use standard data like credit scores, but they often miss valuable information hidden in detailed credit reports. Our project aims to use advanced artificial intelligence, specifically transformer models, to analyze raw credit bureau data more effectively. By doing this, we can create a more accurate and efficient way to evaluate credit risk. This will benefit our partner organization by improving their lending decisions, reducing financial risk, and increasing overall efficiency in their operations.

Faculty Supervisor:

Vahab Khoshdel

Student:

Partner:

Wealthsimple Technologies

Discipline:

Computer science

Sector:

Information and cultural industries; Mining

University:

University of Manitoba

Program: