AI Case Study
Recurly recovers 70% of previously declined card payments through predicting best retry date using using ra random forest model
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.
Industry
Financial Services
Banking
Project Overview
According to the Recurly: "The Recurly Revenue Optimization Engine utilizes machine learning to create a tailored process to repair failed credit and debit card transactions." Using a random forest model, the software predicts the best date to retry processing a subscription card payment.
Reported Results
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".
Technology
"Once the data has been gathered and cleaned, the work of training the model begins. We have one dependent variable (whether or not a transaction succeeds) and dozens of independent variables (like the day of week, the credit card brand, etc.). The model then assesses which of the independent variables has the most impact on transaction success. Once the model has been trained, we validate the model by using other data that wasn’t in our training set. It’s crucially important to train and test on different data, because the model must be robust enough to make accurate predictions about data it has never seen before."
Function
Operations
Network Operations
Background
Recurly is a subscription payment management vendor which services businesses globally.
Benefits
Data
"[H]undreds of millions of payment transactions from thousands of subscription businesses" dating back to 2009.