How many commodity rules were tested, and how many held up?

25 rules were tested on the commodity face as of 6 Nov 2026: 7 validated, 5 provisional, 2 descriptive and 11 found no edge.

What does validated mean here?

A rule is validated only when its 95% range excludes zero, both halves of the history agree, it has at least 20 separate windows and 10 episodes, and it survives a false-discovery check (q at or below 0.10) across all 108 tests. In-sample: these rules were written down after a first look at the same history, so every label here is in-sample. Only results logged from 2026-09-25 onward (the forward ledger) are truly out-of-sample.

Which commodity signals were tested, and which held up

Every rule the commodity face reads: stock betas to oil, gold and copper, oil implied volatility and dips, curve, momentum and positioning rules, with the sample behind each result.

Data as of 6 Nov 2026.

Open the commodities evidence in the cockpit

As of 6 Nov 2026, 25 rules were tested on the commodity face: 7 validated, 5 provisional, 2 descriptive and 11 found no edge.
Across all four faces the false-discovery check covers 108 tests: 29 validated, 19 provisional, 12 descriptive and 48 with no edge.
Validated (7) on this face: Brent → XLE after SPY; Gold → GDX (gold miners ETF) after SPY; Copper → NSE Metal index after Nifty; Brent → OMC basket (BPCL, IOC, HPCL equal weight) after Nifty; and 3 more.
Provisional (5): When crude (CL, roll-free) has risen over 21 sessions by at least its trailing-5-year 80th percentile; Share of days on which crude's next-21-session roll-free move stayed inside the 1-sigma band implied by OVX (OVX/sqrt(12)); OVX ≥ trailing-3y 80th pct → higher odds of a ≥ 7% Nifty dip within 21 NSE sessions; OVX ≥ trailing-3y 80th pct; and 1 more.
No edge found (11): WTI curve in backwardation (CL2! below CL1!, same session, unadjusted) → XLE beats SPY over the next 63 sessions; Cross-sectional commodity carry; Cross-sectional commodity momentum; Gold 'crowded long'; Brent → USD/INR (no market control); and 6 more.
In-sample: these rules were written down after a first look at the same history, so every label here is in-sample. Only results logged from 2026-09-25 onward (the forward ledger) are truly out-of-sample.

Rules that held up or came close

Effect = the gap against a volatility-matched or ordinary day (percentage points of odds, or % of return; a plain coefficient for betas and rank correlations). Windows = separate, non-overlapping periods the rule could be judged on.
Rule tested	Result	Effect	95% range	Windows	Episodes	Halves
Brent → OMC basket (BPCL, IOC, HPCL equal weight) after Nifty. Weekly (Fri-Fri) log return of the target regressed on the driver's roll-free log return AND the market's log return; beta = extra % move of the target per 1% driver… Target: OMC weekly excess beta to Brent.	Validated	-0.11	-0.21 to -0.030	562	562	agree
Brent → paints (Asian Paints, Berger equal weight) after Nifty. Weekly (Fri-Fri) log return of the target regressed on the driver's roll-free log return AND the market's log return; beta = extra % move of the target per 1% driver… Target: Paints weekly excess beta to Brent.	Validated	-0.13	-0.17 to -0.098	562	562	agree
Brent → ONGC + Oil India (equal weight) after Nifty. Weekly (Fri-Fri) log return of the target regressed on the driver's roll-free log return AND the market's log return; beta = extra % move of the target per 1% driver move beyond… Target: ONGC/OIL weekly excess beta to Brent.	Validated	+0.26	+0.19 to +0.31	562	562	agree
Brent → XLE after SPY. Weekly (Fri-Fri) log return of the target regressed on the driver's roll-free log return AND the market's log return; beta = extra % move of the target per 1% driver move beyond what the market explains.… Target: XLE weekly excess beta to Brent.	Validated	+0.41	+0.34 to +0.48	879	879	agree
Gold → GDX (gold miners ETF) after SPY. Weekly (Fri-Fri) log return of the target regressed on the driver's roll-free log return AND the market's log return; beta = extra % move of the target per 1% driver move beyond what the… Target: GDX weekly excess beta to gold.	Validated	+1.75	+1.61 to +1.91	879	879	agree
Copper → FCX after SPY. Weekly (Fri-Fri) log return of the target regressed on the driver's roll-free log return AND the market's log return; beta = extra % move of the target per 1% driver move beyond what the market explains.… Target: FCX weekly excess beta to copper.	Validated	+1.06	+0.82 to +1.32	538	538	agree
Copper → NSE Metal index after Nifty. Weekly (Fri-Fri) log return of the target regressed on the driver's roll-free log return AND the market's log return; beta = extra % move of the target per 1% driver move beyond what the… Target: NSE Metal weekly excess beta to copper.	Validated	+0.25	+0.18 to +0.32	796	796	agree
When crude (CL, roll-free) has risen over 21 sessions by at least its trailing-5-year 80th percentile, NSE Energy beats the Nifty over the next 63 NSE sessions (signal moved to the next NSE session). Target: NSE Energy - Nifty, next 63 sessions.	Provisional	+1.36%	-0.07% to +2.82%	50	21	agree
Share of days on which crude's next-21-session roll-free move stayed inside the 1-sigma band implied by OVX (OVX/sqrt(12)), minus the 68.27% a normal curve would hold. Mar 15 - May 15 2020 excluded (negative-price episode). Target: CL 21-session move inside the OVX 1-sigma band (share minus 68.27%).	Provisional	+5.2 pp	+1.6 pp to +8.7 pp	217	217	agree
OVX ≥ trailing-3y 80th pct → higher odds of a ≥ 7% Nifty dip within 21 NSE sessions. Target: Nifty ≥7% dip within 21 sessions.	Provisional	+5.4 pp	-0.2 pp to +11.6 pp	62	19	agree
OVX ≥ trailing-3y 80th pct → higher odds of a ≥ 7% dip in the OMC basket within 21 NSE sessions (signal moved to the next NSE session). Target: OMC basket ≥7% dip within 21 sessions.	Provisional	+8.1 pp	-0.6 pp to +17.5 pp	44	15	agree
OVX (CBOE crude-oil implied vol) at or above its trailing-3y 80th percentile → higher odds that XLE closes ≥ 7% below today's close within 21 sessions (signal moved to the next session: OVX closes 16:15 ET, after the 16:00 equity… Target: XLE ≥7% dip within 21 sessions.	Provisional	+9.6 pp	+1.9 pp to +17.4 pp	64	18	agree
OVX ≥ trailing-3y 80th pct → higher odds of a ≥ 7% NSE Energy dip within 21 NSE sessions. Target: NSE Energy ≥7% dip within 21 sessions.	Descriptive	+2.9 pp	-3.2 pp to +10.0 pp	62	19	disagree
OVX ≥ trailing-3y 80th pct → higher odds of a ≥ 7% SPY dip within 21 sessions (signal moved to the next session). Target: SPY ≥7% dip within 21 sessions.	Descriptive	+4.5 pp	-1.2 pp to +10.8 pp	64	18	agree

Tested, no edge

These rules were stated in advance and found nothing on this history; they stay on the record.

Rule tested	Effect	95% range	Windows
WTI curve in backwardation (CL2! below CL1!, same session, unadjusted) → XLE beats SPY over the next 63 sessions.	+1.48%	-0.84% to +4.06%	39
Cross-sectional commodity carry: each month-end rank the roots with a listed second month (CL BRN NG GC HG ZC) by ln(front/second) (+ = backwardation); next-month roll-free return of the top third…	+0.72%	-0.38% to +1.83%	381
Cross-sectional commodity momentum: each month-end rank 12 roots (CL BRN NG GC SI HG ZC ZS ZW KC SB CT) by roll-free return over months t-11..t-1 (skip the latest month); next-month return of the top…	+0.36%	-0.33% to +1.08%	381
Gold 'crowded long': managed-money net long (CFTC disaggregated, long - short) as a share of futures open interest at or above its trailing-156-week 80th percentile, known 3 business days after the…	+0.76%	-4.31% to +5.90%	27
Brent → USD/INR (no market control). Tests the belief 'oil up = rupee down' as same-week co-movement. Weekly (Fri-Fri) log return of the target regressed on the driver's roll-free log return AND the…	-0.012	-0.034 to +0.006	879
Big oil month (same rule) → USD/INR rises (rupee weakens) over the next 63 sessions.	-0.38%	-0.93% to +0.12%	50
Big oil quarter (CL 63-session roll-free return ≥ trailing-5y 80th pct) → USD/INR rises over the next 63 sessions.	-0.14%	-0.88% to +0.52%	35
Copper/gold ratio 63-session change in its trailing-5y top tercile → the US 10-year yield rises over the next 63 sessions ('copper/gold leads yields').	+1.41%	-8.32% to +10.75%	42
Copper/gold ratio (roll-free) 63-session log change in its trailing-5y top tercile → XLB (US materials) beats SPY over the next 63 sessions.	+0.09%	-0.84% to +1.00%	44
Big oil month (same rule) → OMC basket lags the Nifty over the next 63 NSE sessions (the textbook 'OMCs suffer after oil spikes').	+0.12%	-2.77% to +2.68%	31
Big oil month (CL 21-session roll-free return ≥ trailing-5y 80th pct) → XLE beats SPY over the next 63 sessions.	-0.46%	-3.30% to +2.42%	50

How old is each input?

Every input the face reads, and how old it is.
Input	Latest data	Age	On time
NYMEX:CL1!	6 Nov 2026	1 business day	yes
ICEEUR:BRN1!	6 Nov 2026	1 business day	yes
COMEX:HG1!	6 Nov 2026	1 business day	yes
COMEX:GC1!	6 Nov 2026	1 business day	yes
NYMEX:NG1!	6 Nov 2026	1 business day	yes
CBOE:OVX	6 Nov 2026	1 business day	yes
CBOE:GVZ	6 Nov 2026	1 business day	yes
AMEX:XLE	6 Nov 2026	1 business day	yes
AMEX:SPY	6 Nov 2026	1 business day	yes
NSE:NIFTY	6 Nov 2026	1 business day	yes
FX_IDC:USDINR	6 Nov 2026	1 business day	yes
Daily stock and ETF price history	6 Nov 2026	1 business day	yes
Rule tests (re-measured weekly)	3 Nov 2026	4 business days	yes
Commodity futures board snapshot	6 Nov 2026	1 business day	yes

How to read the labels

Validated: the 95% range excludes zero, both halves of the history agree in sign, there are at least 20 separate windows and 10 episodes, and it survives the false-discovery check (q at or below 0.10) across every macro test.
Provisional: the 95% range (or the 90% range) excludes zero but one of the other validation checks fails: a tilt, not a rule.
Descriptive: context only: the range includes zero or there were too few cases to test.
No edge: a test stated in advance that found no edge on this history.
Fact: arithmetic (currency translation, hedge cost), not a statistical claim.

Method: each effect is the gap against a volatility-matched or ordinary day, with a 95% range from a circular moving-block bootstrap (2,000 resamples, fixed seed). Prices and indicators are TradingView closes; how the numbers are made; the cockpit's forecasting models are validated separately on the model research page.

Questions

How many commodity rules were tested, and how many held up?: 25 rules were tested on the commodity face as of 6 Nov 2026: 7 validated, 5 provisional, 2 descriptive and 11 found no edge.
What does validated mean here?: A rule is validated only when its 95% range excludes zero, both halves of the history agree, it has at least 20 separate windows and 10 episodes, and it survives a false-discovery check (q at or below 0.10) across all 108 tests. In-sample: these rules were written down after a first look at the same history, so every label here is in-sample. Only results logged from 2026-09-25 onward (the forward ledger) are truly out-of-sample.

More from the Macro tab: all five faces · Risk gauges · FX · Crypto · Bonds.