The project was born from the idea of overcoming the existing prospect business screening framework, considered too limiting, by associating each customer with not only an alleged credit behavior, but also all the information necessary to calculate the potential value of a customer.
This forecast is made customer by customer and therefore varies according to all potential characteristics, such as the proposed payment method or the product being sold. More marginal products or a particularly long expected life could in fact result in a higher expected customer value, thus making it acquirable.
Description and Benefits
Moxoff has developed a series of machine learning models and tools for the personalized and dynamic estimation of all those aspects of potential customers that impact on the expected value of the prospect.
For each business customer, the creditworthiness, the expected life and the NPV (Net Present Value) are therefore estimated based on the conditions that could be proposed. Therefore, each customer has different possibilities based on the products offered or the payment methods chosen by the customer.
A further tool, made up of transparent rules and fully customizable by the Client, decides the optimal policy downstream of these possible combinations, resulting in an acquisition with the most tactical product or in a rejection. The result is communicated to the field sales agent via a web interface accessible from a tablet.
- New clients,enlargement of the audience that can be acquired thanks to a personalized, dynamic and timely estimate of the customer’s value
- Improved accuracy, formalization of the credit dynamics of prospects in order to guide the sales force with ad hoc analyzes based on the characteristics of the customers discovered by the models and in a geographically more widespread way
- Greater independence, reduced dependence on external data providers such as credit bureaus