This model is a regime/structural-change detection layer intended to reduce overconfidence under distribution shift and improve discretionary calibration.

The model is built as a multi-layer ensemble with a decision-tree, trees are fused via Rule-fit; Trees aggregation enable a lower risk of overfit over the underlying mechanism of trees. Its differentiator is the training and evaluation setup: zero-shot forecasting across heterogeneous markets plus non-market timeseries (weather, energy, ECG-like signals of different behaviors to enforce invariance and penalize domain-specific overfitting over task generalization.

The pipeline emphasizes feature hygiene and interpretability: signal-to-noise screening, residualisation/whitening/normalization, redundancy controls, and partial-dependence-driven checks. The objective is a detector that fires on structural change patterns (breaks, phase shifts, observability loss, aleatoric uncertainty) and outputs actionable calibration signals (risk throttles, model confidence caps) suitable for downstream discretionary or systematic decision rules.