Raphael Meira Lima
Back to cases

Banking · 2014-2015

Itaú Unibanco: A major Brazilian financial institution

Problem
Improve credit decision quality across the lifecycle while keeping risk and delinquency under control.
Role
Data scientist on credit risk and decision engines.
Approach
Application and behaviour scoring, portfolio monitoring, expected-loss thinking, and policy alignment.
Impact
Contributed to credit-risk modeling and portfolio monitoring that supported disciplined origination as Itaú’s credit portfolio reached R$548.1 billion in 2015, up 4.3% year over year, with 90-day NPL at 3.5% and coverage at 164%.
Lessons
Durable credit outcomes come from policy and monitoring, not from a single model.

Related capabilities

  • Credit risk decisioning
  • Applied machine learning
  • IFRS 9 & expected loss

Employers are named and consulting clients stay anonymized. Company-level figures such as portfolio size, GMV or delinquency show the context of the period in which the work took place.