Generalized Groves of Neural Additive Models: Pursuing transparent and accurate machine learning models in finance
This work addresses the need for interpretable models in highly regulated financial industries, though it appears incremental as it builds on existing neural additive models.
The authors tackled the problem of balancing accuracy and transparency in machine learning for finance by introducing generalized groves of neural additive models, which separate features into linear, individual nonlinear, and local interacted nonlinear categories, demonstrating high accuracy and transparency with predominantly linear and sparse nonlinear terms in empirical examples.
While machine learning methods have significantly improved model performance over traditional methods, their black-box structure makes it difficult for researchers to interpret results. For highly regulated financial industries, model transparency is equally important to accuracy. Without understanding how models work, even highly accurate machine learning methods are unlikely to be accepted. We address this issue by introducing a novel class of transparent machine learning models known as generalized groves of neural additive models. The generalized groves of neural additive models separate features into three categories: linear features, individual nonlinear features, and interacted nonlinear features. Additionally, interactions in the last category are only local. A stepwise selection algorithm distinguishes the linear and nonlinear components, and interacted groups are carefully verified by applying additive separation criteria. Through some empirical examples in finance, we demonstrate that generalized grove of neural additive models exhibit high accuracy and transparency with predominantly linear terms and only sparse nonlinear ones.