Acordo Certo Reduces Consumer Debt in Brazil with H2O.ai
$10M of debt retired per month
70% reduction in model development time
Improved model accuracy to nearly 80%
Acordo Certo is Brazil’s largest online debt payment and re-negotiation platform. Based in São Paulo, the company was established in 2015 with a mission to transform the debt industry by helping people reduce debt and help creditors collect in a more seamless and predictable way.
Consumer debt was rising in Brazil, and it was becoming challenging for both consumers and debtors to find solutions. The target market of debtors and the ensuing volume of data to be analyzed were both large and therefore, challenging. Acordo Certo had a small team of data scientists, who were using traditional methods to collect and analyze data, as well as to build and deploy predictive and scored models. However, due to the large database of customers, there was a need to increase the agility of model development and accuracy, as well as improve overall trust in AI by making the results of machine learning algorithms transparent to business partners, such as retailers and banks.
Driverless AI is not only easy to use, but it is easy to get results. We have reduced the time to build and deploy models from about one week to a few days. This is massive for our team. We have also improved the predictive accuracy of the repayment model to over 76% Consumers and creditors alike are reaping the benefits of our unique AI debt scoring models.
Andre Monteiro, Founder and CTO of Acordo Certo
Powered by H2O Driverless AI H2O Driverless AI empowered the small team of data scientists at Acordo Certo to create new models and scores in a much faster and accurate way with automatic feature engineering and then review the results with machine learning interpretability.
AI and machine learning have allowed Acordo Certo to better focus on consumer signals about changes in income and interest in repaying debt. With 3.6M Braziallians on the platform and by using H2O Driverless AI, Acordo Certo was mainly able to:
- Retire over $10M/month
- Reduce the model development time by 70%
- Improve the and the model accuracy to nearly 80%.
These results are making it easier for Acordo Certo to expand its business partnerships with retail and banking firms who want to recoup outstanding consumer debt. Placing technology and machine learning at the center of their approach to the consumer debt market has put Acordo Certo in the unique position of observing consumer signals about changes in income and interest in repaying debt before creditors or lenders. Ultimately, Acordo Certo’s innovative approach is to help consumers, creditors, and lenders alike.