Case Study: Acordo Certo reduces consumer debt and speeds model development with H2O.ai Driverless AI

Acordo Certo cuts model development time 70% with H2O.ai

Acordo Certo, Brazil's largest online debt payment and re-negotiation platform, faced a challenge with its small data science team. They were using traditional methods to build debt scoring models, a process that was too slow for the large volume of data they needed to analyze. They needed to develop models faster and more accurately, and required results transparent enough for their retail and banking partners to trust. To address this, they turned to vendor H2O.ai and implemented its H2O Driverless AI platform.

The solution from H2O.ai used automatic feature engineering and machine learning interpretability, which allowed Acordo Certo's team to build and deploy new models far faster. This transparency gave partners the confidence to trust the AI debt scores. As a result, Acordo Certo now retires over $10M of consumer debt per month. They cut model development time by 70% and improved model accuracy to nearly 80%, enabling them to expand partnerships and help more Brazilians reduce their debt.

Acordo Certo