How Acordo Certo uses H2O.ai
70%
“cut model development time by 70%”
As published on h2o.ai. Checked by usedby on Oct 17, 2026.
What happened
Acordo Certo, a Brazilian online debt payment and re-negotiation platform, uses H2O Driverless AI to build and deploy debt scoring models faster. Automatic feature engineering and machine learning interpretability let a small data science team produce scores that retail and banking partners can trust.
Summary written by usedby from the source page, in English. The figures are those of H2O.ai and Acordo Certo, not ours.
- $10M“Acordo Certo now retires over $10M of consumer debt a month”
- 80%“improved model accuracy to nearly 80%”
- 3.6 million“3.6 million Brazilians on the platform.”
- 76%“improved the repayment model's accuracy to over 76%”
With Driverless AI, Acordo Certo now retires over $10M of consumer debt a month, cut model development time by 70%, and improved model accuracy to nearly 80%.
We have reduced the time to build and deploy models from about a week to a few days, and improved the repayment model's accuracy to over 76%. This is massive for our team.
What the story claims, and what we checked
What we compared with the page.
- The figure: 70%CheckedPrinted word for word on the page, near the name of Acordo Certo.
- The passage quoted aboveCheckedCopied word for word from the page, near the name of Acordo Certo.
- Acordo Certo uses H2O.aiCheckedConfirmed line.
- The result itselfNot checkedWe quote it; we did not measure it.
More stories
Same company, same tool or same industry.
