Accuracy-Preserving Stability Regularization for Large-Scale Retail Demand Forecasting

• URL: http://arxiv.org/abs/2607.13331v1
• Date: Tue, 14 Jul 2026 23:31:00 GMT
• Title: Accuracy-Preserving Stability Regularization for Large-Scale Retail Demand Forecasting
• Abstract summary: We ask whether a training-time penalty on consecutive within-series movement can improve horizontal forecast-path stability without materially changing point accuracy.<n>The penalty is evaluated in a temporal-structured pipeline combining recent-demand embeddings with calendar, price, hierarchy, item, and store features.<n>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.
• Score: 6.830447377605494
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Stabilizing distribution-free probabilistic forecasts [5.716454975957337]
  We integrate forecast stability alongside forecast quality into the training of distribution-free probabilistic time-series forecasting models.<n>We propose a method for generating stabilized forecasted conditional quantile functions using regression splines parameterized by a neural network.<n>We empirically evaluate the proposed method on two datasets with different statistical properties and show that it can effectively reduce forecast instability without a substantial loss in forecast quality.
  arXiv  Detail & Related papers  (2026-05-27T14:25:05Z)
• LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling [74.94985663101906]
  We present LeapTS, a novel framework that reformulates time series forecasting as a dynamic scheduling process over the prediction horizon.<n>We show that LeapTS improves overall forecasting performance by at least 7.4% while achieving a 2.6$times$ to 5.3$times$ inference speedup over representative Transformer-based models.
  arXiv  Detail & Related papers  (2026-05-11T09:54:02Z)
• Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting [48.263481135566316]
  We present Tyche, a one-step conditional flow model for efficient probabilistic weather forecasting.<n>Experiments on ERA5 at 1.5$circ$ and 6-hour resolution show that our Tyche, using merely a single NFE, matches or exceeds the forecast skill and calibration of state-of-the-art multi-step generative baselines.
  arXiv  Detail & Related papers  (2026-05-07T20:25:28Z)
• Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing [79.88256756334327]
  Self-Distillation Policy Optimization (SDPO) addresses this by providing denser, more targeted logit-level supervision.<n>We propose Sample-Routed Policy Optimization (SRPO)<n>SRPO routes correct samples to GRPO's reward-aligned reinforcement and failed samples to SDPO's targeted logit-level correction.
  arXiv  Detail & Related papers  (2026-04-02T17:29:18Z)
• Deep Time-series Forecasting Needs Kernelized Moment Balancing [56.619037429652984]
  Deep time-series forecasting can be formulated as a distribution balancing problem aimed at aligning the distribution of the forecasts and ground truths.<n>We propose direct forecasting with kernelized moment balancing (KMB-DF)<n>Experiments across multiple models and datasets show that KMB-DF consistently improves forecasting accuracy and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-01-31T13:20:18Z)
• Beyond Accuracy: A Stability-Aware Metric for Multi-Horizon Forecasting [0.0]
  We introduce the forecast accuracy and coherence score (forecast AC score for short) for measuring the quality of probabilistic multi-horizon forecasts.<n>Results demonstrate substantial improvements over traditional maximum likelihood estimation.
  arXiv  Detail & Related papers  (2026-01-15T21:26:57Z)
• Swift: An Autoregressive Consistency Model for Efficient Weather Forecasting [0.8503925197267593]
  We introduce Swift, a single-step consistency model that enables autoregressive finetuning of a probability flow model.<n>Results show that Swift produces skillful 6-hourly forecasts that remain stable for up to 75 days, running $39times$ faster than state-of-the-art diffusion baselines.
  arXiv  Detail & Related papers  (2025-09-30T00:54:24Z)
• Measuring Time Series Forecast Stability for Demand Planning [0.0]
  Time series forecasting is a critical first step in generating demand plans for supply chains.<n>In production systems, demand planners often value consistency and stability over incremental accuracy improvements.<n>We show that ensemble models improve stability without significantly deteriorating (or even improving) forecast accuracy.
  arXiv  Detail & Related papers  (2025-08-13T04:21:37Z)
• Using dynamic loss weighting to boost improvements in forecast stability [0.9332308328407303]
  Rolling origin forecast instability refers to variability in forecasts for a specific period induced by updating the forecast.<n>It was shown that more stable forecasts can be obtained without harming accuracy by minimizing a composite loss function.<n>We show that existing dynamic loss weighting methods can achieve this objective and provide insights into why this might be the case.
  arXiv  Detail & Related papers  (2024-09-26T20:21:46Z)
• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2023-10-17T20:30:16Z)
• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2022-06-16T06:13:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.