Back-dated report: this page was recalculated with the current model and the data published up to 2018-05-25; it was not published live at the time. Charts, analogs and band odds use only information available up to that day. But the model itself was designed on the full 2006–2026 sample, and some macro data are revised figures, so hindsight bias remains; read it with that discount in mind.
Moderate top risk: the index is 5% off its high and internals are still weakening; credit and jobs have not confirmed yet
SPY 272.15, 5.0% below its 52-week high · Unclassified
Key points this week
■
Top-risk score 48.3, moderate risk, +5.9 on last week (10-year percentile: 63%). In back-tests, of the 26 weeks with SPY more than 3% off its 52-week high and a score in the same band, 19% were followed by a drawdown of 10% or more within 3 months (the top probability); the average for all weeks in that position is only 24%, so this band runs at 0.8× the average.
■
Cracks come from: Equal-weight / cap-weight ratio drawdown 2.5% (score 64); % of stocks above 200-day line (top 1,000 by liquidity) 62.8% (score 61).
■
Not yet confirming: Jobless claims off 2-year low +1.1% (score 32); Days the A/D line has lagged SPY's new high 0 days (score 38). If these turn higher, the score moves into a higher band.
■
Fuel 62 (Equity risk premium (1/CAPE − real rate) +2.34% (score 99); Buffett indicator (market cap / GDP) 148% (score 98); Baa credit spread level (low = complacent) 1.84% (score 96)). Fuel sets how far a market falls once it breaks; in back-tests it had no timing power, so it is left out of the headline score.
■
Biggest moves this week: Commodities (silver/oil/base metals), max 3-month gain -34 pts; Jobless claims off 2-year low +24 pts; New highs − new lows, 10-day average +11 pts.
■
Type: Unclassified.
Top-risk score
48.3
Moderate risk▲ +5.9 on the week
Top probability (≥10% fall within 3 months)
19%
Same-position average 24% · this band is 0.8× that
Historical frequency of a ≥10% SPY drawdown within 3 months · sample: 26 weeks in the same band with SPY more than 3% off its 52-week high
Exhibit 1: Odds of a fall over the next 1 and 3 months: this week's band vs the historical average
Scenario
This week (moderate risk)
Same-position avg.
This week vs avg.
All-week avg. (ref.)
Fall ≥5% within 1 month
11%
28%
0.4× (-17 pts)
18%
Fall ≥5% within 3 months
27%
43%
0.6× (-16 pts)
34%
Fall ≥10% within 3 months
19%
24%
0.8× (-5 pts)
15%
Same-position average = all past weeks in which SPY was more than 3% off its 52-week high; this week = the 27 of those weeks whose score was in the same band (moderate risk). Multiples and percentage points compare this week with the same-position average (computed on unrounded odds). Fall = SPY's maximum drawdown from that week's close within the window. Sample 2006-09-08 → 2018-01-26, only weeks whose outcome was known by this week.
1. Score history
Exhibit 2: Top-risk score and SPY (past 3 years, weekly)
Note: headline score = crack score; fuel is background only. Shading shows the bands; red vertical lines are the historical tops used for calibration. Sources: Polygon, CBOE, FRED, CFTC, AAII, CNN, FINRA, multpl; WhyNext calculations.
Exhibit 6: Closest historical analogs (nearest on the six class scores, one per quarter)
Date
Distance
Score then
Next 13 wks return
Next 13 wks max drawdown
2017-05-19
21
43.0
+1.8%
1.4%
2017-03-24
26
28.0
+4.0%
-0.6%
2015-05-08
27
40.9
-1.7%
-2.0%
Note: similar is not the same; small sample, for reference only. Sources: Polygon, CBOE, FRED, CFTC, AAII, CNN, FINRA, multpl; WhyNext calculations.
3. What would prove us wrong
■ Cracks are low. If leading sectors (IWM/XLF/KRE/SMH etc.) fall more than 10% while SPY makes new highs, or HYG/EEM/copper/BTC diverge, the score should go up at once — in January 2026 the Russell peaked only 6 days before the S&P 500.
■ Fuel is not high: even if cracks appear, the expected decline is moderate (more like the 10–19% pullbacks of July 2023 or February 2025).
4. Track record and method
Exhibit 7: All history up to this week: score (4-week average) and SPY drawdown; red lines = Type 2 tops, blue lines = Type 1 tops
Exhibit 8: Historical outcomes by band (weeks with SPY within 3% of its 52-week high)
Band
Score
Weeks
Fall ≥5% in 1 month
Fall ≥5% in 3 months
Fall ≥10% in 3 months
Low risk
< 40
271
8%
21%
5%
Moderate risk
40–50
43
16%
28%
0%
Elevated risk
50–60
17
18%
53%
35%
High risk
≥ 60
17
35%
94%
59%
Average
348
11%
27%
8%
Sample 2006-09-08 → 2018-01-26 (only weeks whose outcome was known by this week); the ≥60 band rests on only a handful of independent episodes, so treat it as a rough scale, not a precise probability.
Predictive power (outcomes known by this week only): with SPY near its high, the score's AUC for a ≥10% drawdown over the next 13 weeks is 0.67 (0.5 = no predictive power); the base rate is 8%, against 23% for the top-scoring 20% of weeks. Method: 27 indicators in 6 classes are first aligned for publication lag, then converted to rolling 10-year percentiles (using only data available before that date). The headline score uses only the "crack" indicators (breadth, credit turning, jobless claims turning, cross-asset divergence); "fuel" indicators such as euphoria, positioning and valuation are background only. Limits: tops caused by a pure positioning squeeze or an outside shock often show no internal deterioration beforehand, and this model finds them hard to flag early.
Important disclosures This page is generated automatically each week by a deterministic quantitative model; no large language model is used in the scoring. All thresholds and probabilities come from historical back-tests since 2006. Independent market tops are few, and future results may differ. This page is for information only and is not investment advice or an offer to buy or sell. Markets carry risk; invest with care.