AML-based customer reference recommendation system to optimize the sales process at a B2B software company

Abstract

As account-based marketing and customer engagement are major sales drivers in B2B companies, this paper aims to examine and improve the customer referencing at a B2B software company. Customer referencing allows prospective customers to interact with existing customers and learn about their experience with the company’s software. Currently, prospects and possible advocates are matched manually, resulting in a time-and resource-intensive procedure. The goal of this paper is to propose a machine learning-driven recommendation system to match prospect requests with the company’s existing advocates based on their similarity.