Data Engineering
Revenue-Enhancing Credit Policy Model
Context
A multinational company involved in the logistics marketplace business sought quantitative strategies to increase one of their most important incomes: the advance loan charged for future payments in a network of thousands of merchants.
Method
We started with Exploratory Descriptive Analysis (EDA) to find patterns among groups and ended up using Machine Learning methods. We used Big Data to evaluate which merchants' characteristics were correlated to credit penetration and created a risk-based pricing strategy. The whole credit policy was revamped applying fast practical tests.
Benefits Achieved
Growth in sales’ effectiveness and substantial increase in overall credit portfolio. Not only that, but the Controller’s team could realize policies adjustments given the merchant’s profiles, a strategy translated into an additional estimated monthly recurring revenue worth approximately USD 40k.