The Flow has not summarised this story yet — read it at arXiv Machine Learning.
arXiv:2606. 03245v1 Announce Type: cross Abstract: Concepts of calibration formalize the compatibility between probabilistic predictions and the respective outcomes.
arXiv:2607. 11653v1 Announce Type: new Abstract: Black-box conditional quantile forecasts are widely used for sequential decisions under asymmetric costs, such as inventory planning in supply chain management.
arXiv:2609.13345v1 Announce Type: cross Abstract: Probabilistic forecasting is central to decision-making under uncertainty, yet its methodological landscape has become increasingly fragmented across...
The paper introduces online, sample‑efficient algorithms that generate forecasts expressed as sets of quantiles over arbitrary probability levels. These forecasts are simultaneously accurate across all proper losses that meet mild regularity conditions, enabling dynamic, multi‑metric prediction in both binary and multiclass settings. The authors illustrate the method by combining expert quantile forecasts of COVID‑19 hospitalizations to provide richer risk information for decision makers.
arXiv:2603.04275v2 Announce Type: replace-cross Abstract: We introduce inference methods for score decompositions, which partition scoring functions for predictive assessment into three interpretable...
arXiv:2607. 26792v1 Announce Type: cross Abstract: Probabilistic K-line forecasting describes uncertainty in four complementary prices, namely open--high--low--close (OHLC).