# Accuracy Is Not Service: A Decision-Aware Benchmark for Intermittent-Demand Forecasting

arXiv: https://arxiv.org/abs/2609.13840 · HTML: https://mlsanity.com/paper/2609.13840/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 33 references that are in the map.
- First posted on arXiv 12 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [Monash Time Series Forecasting Archive](https://mlsanity.com/paper/2105.06643/) (2021)
- [GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation](https://mlsanity.com/paper/2410.10393/) (2024)
- [Chronos-2: From Univariate to Universal Forecasting](https://mlsanity.com/paper/2510.15821/) (2025)
- [The Perils of Learning Before Optimizing](https://mlsanity.com/paper/2106.10349/) (2021)

## Built on by (most cited first, 1 of 1)

- [When, Not How Much: Evaluating Time-Series Foundation Models on Sparse Events](https://mlsanity.com/paper/2609.39386/) (2026)

## Abstract (arXiv)

A contract-logistics spare-parts operator is paid on order-level service: an order counts only if every requested line is fulfilled, yet forecasters are selected based on line-level forecast accuracy. This disconnect matters when demand is intermittent and lumpy, histories are short, and lead times span months. We benchmarked 38 forecasting methods spanning classical, intermittent-demand, machine-learning, deep-learning, and pretrained foundation models. A common decision-aware protocol evaluates them on an industrial panel drawn from a live contract and two public datasets. Forecast-accuracy rank and order-service rank are negatively correlated on the industrial panel, at -0.555, across methods evaluated on 20,330 real multi-item orders. Service is more closely associated with the direction of cumulative forecast bias, including over-prediction during zero-demand periods, than with point accuracy. Examining bias in Chronos-2's instance normalization yields a training-free correction that lifts the per-material fill proxy from 77.5% to 92.0% (14.5 percentage points) at the 90% policy target and raises the complete-order fill rate from 54% to 63%. For reproducibility, we release RUF (Regenerate-Until-Fidelity), a method for generating fidelity-certified synthetic panels on which the findings reproduce. For intermittent demand, the lowest-error forecast need not deliver the highest service. Bias direction helps explain this gap, which can be reduced without retraining.