The shelf · The 38.2% pullback · E-mini Nasdaq-100
The 38.2% pullback on NQ
Short answer: not quite; its score reached a pass, but it missed one of the two checks a pass also needs, and close is not a pass. The 38.2% pullback on NQ, tested by Thinridge on 18.8 years of one-minute E-mini Nasdaq-100 futures data (2008 to 2026) with costs on every trade, made $63,478 net for one contract over 1,622 trades; 104 of 5,000 coin-flip copies of it (the same trades, the side picked at random) did as well or better on the years before 2023. Verdict: Close, 80 of 100.
Where it breaks, and what to change ↓
Swings of 5 bars each side on 5-minute bars. After a swing up, the first pullback to 38.2% of it that closes back above the line buys, with the stop under the swing's low; the mirror after a swing down. Between 9:45 AM and 3:00 PM; out at 3:30 PM. Run on NQ, the E-mini Nasdaq-100. Times are New York time.
What these settings mean
- follow: trades in the direction of the break or signal.
- long and short: takes both buys and sells.
- window: a new trade can start only between these two times.
- out: any trade still open is closed at this time.
- stop past the setup’s extreme: a stop-loss just beyond the setup’s own high (for a sell) or low (for a buy); no profit target.
- bars: the setup is read on bars of this many minutes.
- swings: a swing high (or low) is a bar with this many lower highs (or higher lows) on each side of it.
- The other settings are the setup’s own; the sentence above says what they do.
Tested as written above: a stop one tick past the extreme the setup names, no target, out at 3:30 PM. A different stop or target is a different strategy, with its own result: Test your version →
Hypothetical backtest: one contract, after costs, not real trading. Simulated results have limits: they are not actual trading, they are made with the benefit of hindsight, and no account is likely to achieve results like these. The standard statement
How to read the score. It has to beat 5,000 coin flips on the 15 years before 2023 (2008 to 2022, kept apart from the years since 2023): the same trades with the side picked at random, so they test the side it takes, not when it trades. The years-before-2023 check and the year-by-year check are scored on those years too: with the coin flips, 60 of the 100 points; the other three use all 18. A high score doesn’t mean easy to hold: read the longest wait for a new high. A score is how the setup did against our published checks on 2008 to 2026; it is not a forecast, and what it does next is unknown. How a score is made.
2008 to 2022: 1,317 trades, $52,449. Since 2023, the years kept apart: 305 trades, $11,029.
Patience past noon is where this strategy's money has lived; before noon it paid costs for nothing.
Close: the score is a pass, but a pass also needs two more checks and it misses one: on the years before 2023 the range of likely results runs from -$9,481.40 to $113,643.60, which includes losing money.
How the 80 is made: clean data 5 of 5, the years before 2023 holding up 18 of 25, year after year 11 of 20, the coin flips 13 of 15, higher costs 20 of 20, a nudge to its settings 13 of 15. Passed is 70 or more with two more checks; Close is 40 to 69, or 70 or more that misses a check; Failed is under 40, or failed automatically (too few trades, or money only since 2023). How to read a report
What to do with this
Where it breaks
No side and no weekday loses in both periods: each weakness here shows in one of them, and one period alone can be chance. What holds in both: its shorts, $34,563 and $13,158.
| 2008 to 2022 | since 2023 | |
|---|---|---|
| 10:00 AM | -$4,096 | -$2,246 |
| 11:00 AM | -$9,172 | -$10,939 |
| 12:00 PM | -$24,264 | -$13,419 |
| 1:00 PM | -$11,305 | -$19,520 |
| 2:00 PM | $8,254 | $5,939 |
| 3:00 PM | $36,217 | -$5,351 |
Every number above is counted from this test’s own trades. A red edge loses in both periods, a green one makes money in both. Picking the best tile is fitting: test your own version and it is scored as a second try.
Or test fewer days: only after a wider-than-usual day, or only after a quieter one. Each opens the form with that one change filled in; the run is yours, free, private, by email.
What failed, and what to test next
Per contract, the typical trade was up $235 at its best and down $205 at its worst before it got out, against a stop $460 away.
How the trades moved doesn't point at the stop or the target: no one change to them stands out.
How far each trade went for it and against it before it got out, held against the same trades taken the other way (the side the coin flips take). Read from this test’s own trades; nothing here is run or scored.
A second look: can one change fix it?
Where it stands. It scored 80, enough for a pass, and no part is under half its points. What holds it at Close: on the years before 2023 the range of likely results runs from -$9,481 to $113,644, which includes losing money.
Where it is weak. 2008 to 2022: 1,317 trades, $52,449; since 2023: 305 trades, $11,029. With one tick of slippage each way, as tested, $63,478; with two, $47,258; with three, $31,038. Its five best trades made 55% of its net.
No change offered: nothing in it is broken. It made money on 2008 to 2022 and since 2023, and the score passed it. It is held at Close because, over 2008 to 2022, its trades swing too widely for their number (1,317) to rule out a loss. A change can’t add trades; only more months can. So it is filed as it is, with what its own record says to expect, and checked after each data download: Filed before it happened.
How a second look works: a Close gets at most one change, and only when its own record points at one weakness with a reason from outside these years. The change is written down before it is run, scored by the same checks, and printed with its try count; a pass from a change waits for months nobody has seen before it counts. Of the shelf’s 17 Closes: none with a change offered; 2 with nothing broken, filed as they are; 15 with no change offered.
What we ran next
The next one. No single change is pointed at; the result stands as written.
What to try next. It already trades rarely, on a stock index, where most of what came near is. What the setups that came near share →
Check your own trades
If you trade a version of this, the trade audit holds your own fills against the written rule and shows, in dollars, what your part adds or costs. Audit your trades →
A strategy the form doesn’t know goes by email, about a week.
The same setup on the other markets
Run unchanged, at the same settings, on 11 markets (the shelf’s six and five more; of those five, only a pass or a Close has a page of its own). Each one is its own test: picking the market that did best after the fact is how a backtest flatters itself. ES, NQ, YM and RTY are all stock-index futures and move together, so their agreeing is weaker evidence than it looks.
One setup, tested, every week
The next verdict by email: what was tested, its score, and where it breaks. Free; leave with one click. Nothing on this site is held back for it.
Sent through Buttondown, the newsletter service you join yourself, as Privacy says.
The engine's report, in full
One trade a day, the first signal in the window, on one-minute bars, with one tick of slippage each way and commission. The coin flips are run on the years 2008 to 2022, kept apart from the years since 2023; the rest of the score uses all of them. Tested November 16, 2026, on data to October 30, 2026.
==============================================================
THINRIDGE ENGINE REPORT
==============================================================
SCOPE: FirstRate one-minute data, unadjusted; the rule exactly as locked; nobody checked it by hand.
1. THE RULE AS LOCKED
setup type : Fibonacci retracement
as you locked it:
The 38.2% pullback, at the settings the form starts with, run again on data to Oct 30, 2026: swing 5; ratio 0.382; trigger hold; window 9:45 AM to 3:00 PM; exit 3:30 PM; bar 5; mode follow; sides Both
the years from 2023 kept apart, the split every shelf cell is scored on
as the engine read it:
exit model : stop: one tick past the level the setup itself names (its swing, pattern end, zone edge or swept extreme)
: target: none (time exit)
: time exit: always kept as the backstop
filter : none
tries : #1
bars : signals on 5-minute bars built from the one-minute series by clock bucket; every fill, exit and cost is still on the one-minute series
entries : one trade a day, the first qualifying signal in the window
history : 18.8 years, kept apart from 2023 on (as declared)
: trades dated 2023 or later are kept apart; the coin flips are run on the trades before 2023, the rest of the score on all of them
2. VERDICT
SCORE : 80 / 100
VERDICT : CLOSE
HELD : the score is a pass (80), but a pass also needs two more checks, and it misses:
- on the years before 2023 the range of likely results runs from -$9,481.40 to $113,643.60, which includes losing money
THE SIX CHECKS : clean data 5 of 5; the years before 2023 18 of 25; year to year 11 of 20; the coin flips 13 of 15; costs 20 of 20; nudging a setting 13 of 15
3. RESULT
Trades 1,622 Net $63,477.60 Per trade $39.14
Since 2023 : 305 trades, $11,029.00
Before 2023 : 1,317 trades, $52,448.60
Win rate 49.3% (800 of 1,622 trades closed above zero after costs)
Exits by type: stop 361, time 1261
How it splits (every trade, one contract after costs):
trades net average winners
Long 933 $15,756.40 $16.89 51%
Short 689 $47,721.20 $69.26 48%
Monday 329 $15,808.20 $48.05 48%
Tuesday 340 $727.00 $2.14 48%
Wednesday 310 $13,913.00 $44.88 51%
Thursday 341 $43,197.80 $126.68 51%
Friday 302 -$10,168.40 -$33.67 49%
A split is something to look at, not a new rule: keeping only the best side or day is a new version,
and testing it counts as one more try.
Time in a trade: half the trades last 2 h 29 min or less; the middle half between 1 h 21 min and 3 h 39 min; the longest 5 h 44 min.
4. THE COIN FLIPS (5,000 copies of the rule that pick the side at random)
Full window p = 0.0286 (143 / 5,000)
Before 2023 p = 0.0208 (104 / 5,000) <- the one the score uses
Counting earlier tries, p (try #1) = 0.0208
5. YEAR BY YEAR (each year before 2023 a window)
Years 15 profitable 8 profit factor before 2023 / since 1.14
Largest year 2022 = 73.1% of the net before 2023
By year before 2023: 2008 $656.60 2009 $2,942.40 2010 $456.40 2011 -$962.20 2012 -$3,003.20 2013 -$2,619.80 2014 -$3,725.60 2015 -$1,094.00 2016 $397.80 2017 -$526.60 2018 $4,482.00 2019 -$1,454.60 2020 $14,396.80 2021 $4,179.40 2022 $38,323.20
6. COST STRESS (re-simulated)
1 tick $63,477.60 2 ticks $47,257.60 3 ticks $31,037.60
net kept after costs at 1 tick 73.4% profit factor at twice the costs 1.08 Breakeven 4.9 ticks/side
7. FRAGILITY (5,000 resamples of the trades, drawn with replacement)
Full CI -$27,532.40 .. $156,397.60 P(net>0) 0.9204
Pre-2023 CI -$9,481.40 .. $113,643.60 P(net>0) 0.9528
bad-case drawdown (95th percentile) / actual 1.38x Top trade 12.1% Top-5 55.0%
8. NUDGING A SETTING (the main setting moved 10% either way)
Net kept on the nudge 95% Turned to a loss: no Settings 5
9. COULD YOU HOLD IT (no points)
Longest stretch without a new equity high: 119 months (ending 2020-05)
Rolling 12-month windows negative: 47% of 215 Worst 12 months: -$8,707.40 (ending 2021-08)
Max drawdown $36,255.40 Median year $456.40 Years of median to recoup the drawdown: 79.4
Share of all profit from the best two years: 95%
10. THE CODE FILE (offered when all five hold)
[x] passed
[x] fewer than 1 in 20 coin flips matched it on the years before 2023, counting earlier tries
[ ] the range of outcomes on the years before 2023 stays above zero
[x] it breaks even at 4 ticks of cost a side or more
[x] no single trade is over 25% of the net
=> not offered at this result.
11. HOW THE POINTS WERE COUNTED (each measure, then the points it earns)
II, the years before 2023: steadiness kept on the years before 2023 (Sharpe ratio) 2.42 (per-trade) → 15 points; money on the years before 2023 → 3 points
III, year to year: years profitable 0.53 → 3 points; profit factor before 2023 / since 1.14 → 8 points; one year's share → 0 points
IV, the coin flips: coin-flip p 0.0208 (5,000 coin flips) → 8 points; bad-case drawdown / actual 1.38 → 4 points; top trade 0.121 → 1 point
V, costs: net kept after costs 0.734 → 12 points; profit factor at twice the costs 1.08 → 8 points
VI, nudging a setting: net kept on a nudge 0.95 → 8 points; settings counted 5 → 2 points; turned to a loss: no → 3 points
12. THE AUTOPSY (where the money came from and went; the rule as it ran, no new try)
Exits: time 1,261, $368,298.80; stop 361, -$304,821.20
On the books, before 2023 (net $52,448.60): 10:00 AM -$4,096.00 11:00 AM -$9,172.20 12:00 PM -$24,263.80 1:00 PM -$11,304.80 2:00 PM $8,254.40 3:00 PM $36,217.40
Share of the money before 2023 after 12:00: 146%; after 14:00: 84%
Before 2023 $52,448.60, since 2023 $11,029.00 (17% of the net); largest year before 2023: 2022 = 73% of the net before 2023
Nudging a setting 10%: 95% of the net kept; turned to a loss: no
Flat stretch: 119 months without a new high (ending 2020-05); median year $456.40; years of median to recoup 79.4
The money lived after noon: 146% of the money before 2023 was on the books after 12:00 PM. One year is most of it: 2022 is 73% of the net before 2023. Longest wait for a new equity high: 119 months, median year $456.40.
No single change is pointed at: the verdict stands as written. Where it breaks, by side and by weekday, is under How it splits (3. RESULT); each is one change to test as a second version, scored with a tighter bar.
13. IF YOU TRADE THIS BY EYE
Patience past noon is where this rule's money has lived; before noon it paid costs for nothing.
That is what the record says about the rule as written. It is not what next year says.
WHAT THIS CANNOT TELL YOU: the score assumes this rule walked in
once (see tries) and that your development did not touch the
years before 2023. Only you know both. Not investment advice. No
guarantee of future results. Statistical analysis of a mechanical
rule as submitted.
==============================================================
Raw market data: FirstRate Data (firstratedata.com). Statistical analysis of a mechanical strategy as written; not advice.




