Entropy
Shannon entropy H(P) = −Σ p log p is the expected surprise of a distribution — a measure of uncertainty used in information theory, portfolio tilts, and some max-ent priors.
Definition
Entropy refers to a measure of uncertainty used in information theory, portfolio tilts, and some max-ent priors. Keep that definition fixed when comparing series, managers, or regimes — renaming the same tape does not create a new signal.
Why it matters
It is a named object desks use to frame risk, positioning, or process. When a measure of uncertainty used in information theory, portfolio tilts, and some max-ent priors shifts, related hedges, limits, and narratives usually need an explicit update rather than a quiet assumption.
Case
Suppose a desk is positioned for the opposite of what entropy is saying. If a measure of uncertainty used in information theory, portfolio tilts, and some max-ent priors moves against that book, the first question is not “is the story clever?” but whether size, hedges, and stop logic still match the observation.
How to read it
Keep the definition fixed, then challenge it with cross-checks before sizing. Prefer a short written null hypothesis for Entropy: what would falsify the current reading in the next window?