S&P 500 · daily · filtered posterior

Market Rotation Metrics

Is the S&P 500 rotating — and is a new rotation starting? Read at two grains — the finer industries (where leadership shifts first) and the 11 sectors, each stripped of the market's move and any single mega-cap — plus Rotation Intensity, a volume-and-turbulence gauge backtested against the rotation institutions actually executed (13F).

Industries
/ 1.00 Rotation probability
Sectors11 GICS
/ 1.00 Rotation probability
Rotation Intensity13F ρ +0.51
pctile vs 1990– history
Volume-spike and turbulence — the gauge that best tracked the real 13F rotation.
The rotation map

Where the money is rotating — by industry

Every industry as a tile. Colour is the move — the market-denoised residual over the industry's current trend (green leading, red lagging, stronger color = bigger move). Size is persistence — how many days it has held that trend, and a one- or two-day blip doesn't reset it. So a big green tile is an established rotation in; a small, vividly-colored tile is a fresh move just starting — the early signal. Hover any tile for the detail.

LaggingLeading longer trend → bigger tile
Young-rotation flag

Is a new rotation starting right now?

Our rule only calls a rotation after five straight qualifying days, so by the time it speaks, the first four days are gone. This flag asks the forward question instead: a candidate run is underway right now — will it survive to five and confirm? Most do not. No candidate run is open right now — there is nothing to forecast until dispersion, leadership and breadth all qualify on the same day.

No open candidate run

The flag appears when a run starts.

Scored 0.812 on 2021+ data it never saw, against 0.736 for a null that only knows how many days the run has lasted (297 runs tested; calibration error 0.0031).

One grain finer — where rotation shows first

Which industries are rotating?

The 11 sectors are coarse: a rotation can tear through one industry while the sector it belongs to barely moves. This is the same market-denoised residual, one level down — where the real leadership shift usually shows first.

Industries rotating in
Industries rotating out
The zoomed-out backdrop

Sector leaders & laggards

Market-denoised residual return — each sector net of its own beta to the index, so what remains is genuine relative movement, not the market carrying everyone together. Breadth is the share of a sector's members actually participating.

Leading into favor
Lagging out of favor
Beyond one model

Regime metrics — choose the gauge you trust

The probability above is one model's read. Here are the recognized rotation & regime measures, each computed from our own equal-weight sector data and charted as its percentile versus its own history (0 = calm for that measure, 100 = its most extreme). We backtested every one against the sector rotation institutions actually executed — reconstructed from ~580 funds' quarterly 13F filings — and the ρ vs 13F on each chip is how closely it tracked that real rotation. Toggle any on to compare. Rotation Intensity — days with both a volume spike and elevated turbulence — matched the real rotation best.

The model and Rotation Intensity answer different questionsare we in a rotation regime (a calibrated probability) versus how much rotation is happening vs history (a percentile) — so a Calm model beside an Active intensity is information, not a contradiction. When they agree it's corroboration; when they diverge it's a signal. We publish both rather than blend them into one number: a naive combination we tested tracked real rotation worse, not better.

0 · calm for this measurepercentile vs 1990–today100 · extreme
How & why we backtested

A rotation gauge is only worth watching if it matches rotation that actually happened. Our model detects whether the market is rotating — it cannot tell us we picked the right measure. So we went to ground truth: the sector bets large institutions actually made. From ~580 funds' quarterly 13F filings, 2013–2026 we reconstructed the real quarter-by-quarter rotation the crowd executed, then scored each measure by how closely it tracked it (Spearman ρ), across 51 quarters.

To stay honest we held out data the search never saw and re-checked every winner out-of-sample (test ρ 0.69–0.75 across 5 splits), and we ran a shuffle-null — letting the optimizer loose on scrambled targets to measure how much a good-looking score is just luck. The winning gate cleared it (p=0.014); a three-signal version overfit — its in-sample fit rose while its out-of-sample score fell, so we stopped at two.

Honest limits: the 13F yardstick is itself imperfect (institutions look a lot like the market and file ~45 days late), the sample is 51 quarters, and this measures rotation intensity — that it is happening — not which sector wins. Which gauge you trust is a choice; that is why they are all here.

What we can and can't claim

Does it actually work?

A latent-state model will always fit something. The only honest test is whether it detects rotation out-of-sample, on data held back from fitting. Here is that record for the sector model, plus the places it is deliberately weak. The industry model runs the identical battery one grain down — its own holdout and cross-validated AUCs are shown on its card at the top.

Sealed-holdout AUC
Detection accuracy on 2021+, tested once. 0.50 is a coin flip.
Cross-validated AUC
Blocked, purged CV across 1990–2020 — the primary evidence.
Calibration error
Predicted vs. observed on the holdout. Lower is better; this is near-perfect.
Base rate to beat
Share of days in rotation. Anything below this AUC would be worthless.

Detection strong

Identifying whether we are in a rotation today is where the model earns its keep — confirmed on a holdout it never saw, well-calibrated, and stable across start dates from 1990 to 2000. The episodes it learned from include every regime a reader would name: the 2000 unwind, 2008, the 2020 shock, the 2022 growth-to-value turn.

Forecasting deliberately modest

Predicting a rotation before it is visible is much harder, and we say so. Forward skill is real but small and decays within weeks. We publish that honestly rather than dress it up — a weak forecast reported plainly is worth more than a strong one that isn't true.

The credibility test

36 years of rotation regimes

The monthly filtered posterior since 1990. Every estimate uses only data available at the time — no look-ahead. Shaded months are model-flagged rotation episodes; the line to the right of the marker is the sealed holdout the model was never fit on.

Rotation probability Flagged episode Sealed holdout · 2021 →
Provenance

How it's built

The same discipline behind asymmetricbeta.com: a high-integrity data island that owns its price feed on one consistent, single-source basis — no unresolved multi-vendor mixing.

Survivorship-free prices

daily bars from a delisting-complete vendor — the companies that left the index are still here. Cross-checked against a second feed at agreement.

Point-in-time membership

S&P 500 constituents and float weights as they actually stood each quarter back to 1990, joined by ISIN — never by ticker, which silently recycles.

Denoised, then modelled

Sector returns net of market beta and single-name concentration, reconciled to independent sector-ETF benchmarks at correlation, fed to a filtered hidden-state model.

Stay current

The rotation reading, in your inbox

A short note when the rotation state shifts — no noise, no marketing. Part of the Gyre Research family. Confirm your email and you're in.

Only email is required. Double opt-in. Unsubscribe anytime. We never share your details.