Abstract: Accounts Receivable (AR), is the most valuable asset of an organization. If it is not managed effectively, it can cause the firm serious financial hardships. Identifying data patterns is essential to understanding AR in order to forecast whether it is guaranteed that an invoice can be paid in a timely manner or else it’ll be delayed. It is extremely important for large organizations that deal with thousands of vendors to fulfill their service level agreements with them to avoid penalties. The data is collected from a multinational organization consisting of the past two year’s transactions. The research has been conducted by reviewing numerous papers related to invoice processing and different methodologies used to estimate consumer payment in AR. This paper is intended to showcase a supervised modeling solution. Predicting the payment outcomes of newly created invoices is essential for facilitating collection actions tailored to each invoice or customer. Since this is a classification problem, an ensemble method of Random Forest and Extreme Gradient Boosting algorithms has been applied. By achieving the highest accuracy, it is possible to determine if the payment for an invoice will be done on or before the due date and provide estimates to the customers regarding delays. This can assist the collection team in prioritizing customers and facilitating their day-to-day work. It is estimated that implementing the model to prioritize the work of the Collection Management team, shall result in a substantial amount of savings. Consequently, the team would contact respective customers or account holders during the period in which the invoices are open, thereby reducing the organization’s accounts receivable.

Keywords: Machine Learning, Invoice Processing, Invoice Payment, Delayed Invoices, Accounts Receivable, Predictive Modeling, Feature Engineering

Published in: 2023 IEEE International Conference on ICT in Business Industry & Government (ICTBIG)