<ul><li>A comprehensive demand forecasting system called "Multi-Stage Hierarchical Forecasting Reconciliation and Adjustment (Multi-Stage HiFoReAd)" has been introduced for Walmart's ad products.</li><li>The system tackles hierarchical time series forecasting and addresses challenges of preserving seasonality, ensuring coherence, and improving accuracy.</li><li>The system utilizes diverse models ensembled through Bayesian Optimization (BO) to achieve base forecasts.</li><li>Experiments on Walmart's internal Ads-demand dataset and public datasets demonstrate significant improvement in error rates and coherence of forecasts at all hierarchical levels.</li></ul>

A Comprehensive Forecasting Framework based on Multi-Stage Hierarchical Forecasting Reconciliation and Adjustment

Discover more