# Global tree forecasters collapse at the hierarchical aggregate: a five-panel failure characterization

arXiv: https://arxiv.org/abs/2609.27912 · HTML: https://mlsanity.com/paper/2609.27912/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 10 of 10)

- [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)
- [Monash Time Series Forecasting Archive](https://mlsanity.com/paper/2105.06643/) (2021)
- [Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globality](https://mlsanity.com/paper/2008.00444/) (2020)
- [Criteria for Classifying Forecasting Methods](https://mlsanity.com/paper/2212.03523/) (2022)
- [Hierarchical forecasting with a top-down alignment of independent level forecasts](https://mlsanity.com/paper/2103.08250/) (2021)
- [Forecasting with Hyper-Trees](https://mlsanity.com/paper/2405.07836/) (2024)
- [Local vs. Global Models for Hierarchical Forecasting](https://mlsanity.com/paper/2411.06394/) (2024)
- [Do Stationarity Transformations Actually Improve Time Series Forecasts? A Controlled Experimental Evaluation](https://mlsanity.com/paper/2605.17689/) (2026)
- [Delta-Based Target Reformulation for Short-Term Electricity Load Forecasting Using LSTM and Transformer Models](https://mlsanity.com/paper/2606.17692/) (2026)

## Abstract (arXiv)

Global forecasting models pool many series and learn one shared function. Gradient-boosted trees are their most common form. We measure a failure of this design that has not, to our knowledge, been documented. Train a global tree on the individual series of a hierarchy, then ask it for the hierarchical aggregate. The aggregate sits far outside the model's training range, and the forecast collapses. The model under-predicts the total by 30-50x in our production deployment, and by up to 496x in a public M5 reconstruction. The mechanism is known: beyond its training range, a tree predicts a constant. It surfaces at the aggregate because the total dwarfs every training series. The cure is not new. Per-series scaling, the preprocessing step that Montero-Manso and Hyndman (2021) recommend, prevents the collapse. So do a weighted aggregate-level training row and seasonal differencing. Our contribution is the characterization. The collapse reproduces on five panels: a production business-to-business marketplace, a synthetic hierarchy, M5, Australian Tourism, and a public business-buyer panel. It holds on three tree libraries, is invariant across training seeds, and is statistically significant. Its onset is immediate and tracks a simple support bound: a scale gap of only 1.15x already costs a third of the total. No standard configuration change prevents it: pooling every hierarchy level into training fails at scale, and the one knob that fits linear models in the leaves softens it without curing it. Rolling the forecasts forward recursively separates the cures: the aggregate-row cure re-collapses, per-series scaling degrades but stays low, and only seasonal differencing keeps its one-step accuracy unchanged. We close with a three-step procedure for diagnosing and preventing the failure in deployed systems.