Customer level predictive modeling for accounts receivable to reduce intervention actions
Abstract
One of the main costsassociated with Accounts receivable (AR) collection is related to theintervention actions taken to remind customers to pay their outstandinginvoices. Apart from the cost, intervention actions may lead to poor customersatisfaction, which is undesirable in a competitive industry. In this paper, westudied the payment behavior of invoices for customers of a logistics company,and used predictive modeling to predict if a customer will pay the outstandinginvoices with high probability, in an attempt to reduce intervention actionstaken, thus reducing cost and improving customer relationship. We defined apureness measure to classify customers into two groups, those who paid alltheir invoices on time (pureness = 1) versus those who did not pay theirinvoices (pureness = 0), and then use their attributes to train predictivemodels, to predict for customers who partially paid their invoices on time (0