Graph neural network for merger and acquisition prediction

Abstract

This paper investigates the application of graph neural networks (GNN) in Mergers and Acquisitions (M&A) prediction, which aims to quantify the relationship between companies, their founders, and investors. M&A is a critical management strategy to decide if the company is to grow or downsize, and M&A prediction has been a challenging research topic in the past few decades. However, the traditional methods of predicting M&A probability are only based on the company's fundamentals, such as revenue, profit, or news. Instead, GNN takes full advantage of those relationship data to expand feature dimension and improve the prediction result. Our M&A prediction solution integrates with the topic model for text analysis, advanced feature engineering, and several tricks to boost GNN. The approach achieves a high Area-Under-Curve score (AUC) 0.952, which is better than the previous record 0.888. The true positive rate is 83% with a low false positive rate 7.8%, which performance is better than the previous benchmark record 70.9%/10.6%.