Home /
Usecases /
Recurly recovers 70% of previously declined card payments through predicting best retry date using random forest model
janhavi
March 18, 2019
Summary:
Recurly has developed a random forest model for its payment processing products which predicts the best day to retry processing a payment for a subscription that has been declined. Recurly claims it can recover 70% of failed payments on average.
Problem:
Recurly claims that its "technology can improve transaction success rates and recovers revenue that would otherwise be lost—up to 12% on average each month" and that it "can recover an average of 70% of failed subscription renewals