A Novel Approach to Predict European Mergers Using Machine Learning Algorithm

Abstract

The European Commission (EC) plays a central role in reviewing mergers and acquisitions (M&A) within the European Economic Area to safeguard market competition and protect consumer interests. The decision-making process is complex, involving assessments of market dominance, competitive overlap, and industry-specific factors, often leading to delayed outcomes for firms and stakeholders. This study applies machine learning (ML) techniques to develop a predictive framework for anticipating EC merger decisions. We evaluate three established classifiers—Random Forest (RF), Support Vector Machine (SVM), and Naive Bayes (NB) on a structured dataset of past EC M&A cases.