Industry 4.0: Predicting lead conversion opportunities with machine learning in small and medium sized enterprises

Abstract

The crisis caused by COVID-19 accelerated processes of changes in the global economy, leading to changes in companies in structures, business models and routines. Small and Medium Enterprises (SME) in particular have faced challenges in finding paths for the journey of digital transformation and adaptation to the industry 4.0 era, which turns integration a key factor. The goal of this work is to predict the likelihood of conversion using Machine Learning (ML), with the purpose of improving the process of converting opportunities in SME in the education sector. The work is based on the Digital Transformation Model for SME (MTD_PMEs), a specific approach in ML technology and Knowledge Discovery in Databases (KDD). The methodology involves a three-step sequence of the KDD_AZ process. Data were collected from a university center in southern Brazil. Results indicate that the 8 attributes used are relevant for forecasting lead conversion and that the chosen technique, Logistic Regression reached a gross precision of 100%, implying an increase in the conversion rate, time savings for the teams and filter leads “unlikely”, helping marketing improvements in its targeting and providing qualified leads.