neuralGAM: An R Package for fitting Generalized Additive Neural Networks

Generalized Additive Models (GAMs) are widely used because of their interpretability and flexibility, while neural networks provide strong predictive performance for complex tasks. This paper introduces neuralGAM, an open-source R package implementing Generalized Additive Neural Networks that combine the interpretability of GAMs with the representational power of deep learning architectures.

The package provides tools for fitting explainable neural additive models by independently training neural networks to estimate the contribution of each feature to the response variable. The implementation supports different neural-network architectures while preserving the additive structure required for interpretability and transparent decision-making.

The paper describes the theoretical foundations of the methodology, the software implementation, and several practical examples demonstrating how neuralGAM can be applied to interpretable machine-learning tasks in statistics, cybersecurity, and applied data science.

Access paper here