PARKED · compute
Hypothesis
RQA metrics (determinism, laminarity) on the recurrence plot of a price window detect impending regime transitions before variance reacts.
Math — recurrence matrix
$$ R_{ij} = \Theta\big(\varepsilon - \|\mathbf{x}_i - \mathbf{x}_j\|\big) $$
Method
Delay-embed returns, build the recurrence matrix, track determinism/laminarity as early-warning. Spot-checked, not fully replayed.
Early-warning literature is suggestive, but RQA is $O(n^2)$ per window and the threshold $\varepsilon$ is finicky. Parked pending a cheap incremental implementation and a proper out-of-sample on transitions.
Critical-slowing-down early-warning signals are real in physical systems; whether they lead financial regime breaks by enough to act on is unproven and expensive to test.