A Comparison of Artificial Neural Network and Multinomial Logit Models in Predicting Mergers

A merger occurs when a bidder firm offers to purchase the control rights in a target firm or when a target firm solicits bids from a bidder firm to purchase the control rights. Predicting merger candidacy is important to measure the price impact of mergers.This study investigates the performance of artificial neural networks and multinomial logit models in predicting merger candidacy. We use a comprehensive dataset that covers the years 1979 to 2004 and includes all deals with publicly listed bidders and targets. We find that both models perform similarly while predicting target and non-merger firms. The multinomial logit model performs slightly better in predicting bidder firms