Search papers, labs, and topics across Lattice.
This paper introduces a training-time penalty for consecutive forecast movements to enhance stability in retail demand forecasting, addressing the limitations of traditional point-error objectives and post-hoc smoothing methods. By integrating recent-demand embeddings with various features in a temporal-structured pipeline, the proposed stability-aware hybrid model significantly improves forecast stability scores over XGBoost while maintaining point accuracy within a minimal range. The results indicate that this approach shifts the evaluation of forecasts towards a balance between accuracy and stability, which is crucial for operational efficiency in retail settings.
Training-time regularization can enhance forecast stability by over 7% without sacrificing point accuracy, challenging conventional forecasting methods.
Retail demand forecasts are reused across replenishment, capacity, labor, and transportation planning cycles. Point-error objectives do not constrain abrupt movement between adjacent forecasts, while post-hoc smoothing acts only after model fitting. We ask whether a training-time penalty on consecutive within-series movement can improve horizontal forecast-path stability without materially changing point accuracy. The penalty is evaluated in a temporal-structured pipeline combining recent-demand embeddings with calendar, price, hierarchy, item, and store features. On selected M5 demand series at 1000, 3000, and 4000-series scales, the stability-aware hybrid model improves Forecast Stability Score over XGBoost by 6.91%, 6.66%, and 7.68%, respectively, while RMSE changes remain within 0.72% across three random seeds. Post-hoc exponential smoothing attains lower raw movement but incurs a larger RMSE cost; training-time regularization preserves more point accuracy and performs favorably under normalized stability. These findings extend forecast evaluation from point-error minimization toward an accuracy-stability trade-off perspective for operational retail forecasting.
