cs.LGNov 9, 2026

Forecast Value Add: Reward-Based Action Selection over Probabilistic Demand Forecasts

Authors: Ankur Verma

Organizations: TrueGradient AI

Abstract

Strong machine-learning ensembles capture much of the trend, seasonality, and known events in demand, yet they can still understate peaks, miss moving events, or mistake temporary changes for shifts in demand level. We address this gap by framing forecast refinement as a reward-driven decision problem. For each forecast period, we let an agent choose among values already produced by the ensemble: its base forecast, distribution-free bounds, quantiles, and a bias-corrected estimate. We evaluate these choices against context-matched historical periods, accounting for calendar position, recurring and moving events, trend, price, and promotions. We then apply a structural seasonal guard to constrain adjustments and record the model, agent, and planner contributions to every published value. We evaluate our approach across five retail, consumer-goods, and direct-to-consumer deployments over nine months. Our refined forecasts reduce mean WMAPE by 6.3% compared with the stacked machine-learning forecast for every customer, with gains reaching 16.7%, and achieve the lowest error in 35 of 45 customer-months. Compared with statistical forecasts, our approach reduces mean error by 18.7%. These results demonstrate that context-aware, auditable action selection can add forecast value beyond a strong ensemble.

Figures & tables

Explore similar work

CardsList
  1. ReasonCast: Agentic Demand Forecasting with Selective Semantic Reasoning

    Aug 15, 2026Ziyue Yang, Chaolin Xu, Yijing Wang +5Retail Demand ForecastingTime Series Forecasting

  2. A Predict-then-Correct Loop Based on Few-Shot Continuous Contextual Bandit for Demand Forecasting

    Jul 17, 2026Zhiwei Lei, Benedict Jun Ma, Ilya JacksonTime Series ForecastingContextual Bandits

  3. Beyond a Universal Forecasting Selector: Demand-Conditioned Model Selection across Demand Patterns and Horizons

    Sep 3, 2026Adolfo GonzálezModel SelectionTime Series Forecasting