Hierarchical Neural Additive Models for Interpretable Demand Forecasts

arXiv:2404.04070v1 Announce Type: new
Abstract: Demand forecasts are the crucial basis for numerous business decisions, ranging from inventory management to strategic facility planning. While machine learning (ML) approaches offer accuracy gains, their interpretability and acceptance are notoriously lacking. Addressing this dilemma, we introduce Hierarchical Neural Additive Models for time series (HNAM). HNAM expands upon Neural Additive Models (NAM) by introducing a time-series specific additive model with a level and interacting covariate components.
Covariate interactions are only allowed according to a …

abstract accuracy arxiv business cs.hc cs.lg decisions demand facility hierarchical interpretability inventory machine machine learning management planning series time series type