Neural networks or statistical additive models: a comparative competition

Jessica Doohan, University of Limerick

Co-authors: Kevin Burke, University of Limerick

Abstract: Neural networks are increasingly being applied to prediction and classification tasks, areas that have traditionally relied on statistical methods. In academic literature, these two approaches are often considered competing techniques for model development. This paper presents a thorough systematic review of studies that compare neural networks with statistical additive models across various application areas.