// STUDY RESULT · 1998-01 TO 2026-09

Inspired by O'Neil: Cup-with-Handle Breakout

NO EDGE

Winners consolidate in a rounded 'cup' with a shallow 'handle', then break out on volume - the entry point of the CANSLIM system.

How this run differs from the source: No cup or handle is found: a 20-day high on heavy volume stands in for the pattern.

	THE STRATEGY	$SPXTR BUY & HOLD
CAGR	4.8%	9.3%
Sharpe ratio	0.32	0.66
Max drawdown	-71.6%	-50.9%

// GROWTH OF $1, LOG SCALE

AMBER: THE STRATEGY · GREY: $SPXTR BUY & HOLD

Out-of-sample (from the split): CAGR 9.2% against 14.0% for the benchmark; Sharpe 0.20 in-sample, 0.49 out-of-sample.

After 25 bps of trading costs: -0.9% a year. WITHIN RANDOM

// DECADE BY DECADE

ERA	STRATEGY	BENCHMARK
1990s	38.4%	20.9%
2000s	-8.0%	-0.8%
2010s	4.1%	14.0%
2020s	18.2%	15.2%

// YEAR BY YEAR, LOSING YEARS IN RED

1998*10.9%27.2%

199970.4%21.0%

2000-36.9%-9.1%

2001-17.8%-11.9%

2002-21.0%-22.1%

200360.6%28.7%

20041.4%10.9%

2005-8.9%4.9%

20062.7%15.8%

200721.6%5.5%

2008-45.1%-37.0%

200910.9%26.5%

201016.2%15.1%

2011-4.1%2.1%

20122.0%16.0%

201339.8%32.4%

2014-6.3%13.7%

2015-9.2%1.4%

2016-15.4%12.0%

201739.9%21.8%

2018-32.6%-4.4%

201931.8%31.5%

202042.4%18.4%

202121.9%28.7%

2022-27.1%-18.1%

202315.4%26.3%

202462.8%25.0%

202534.7%17.9%

2026*-2.9%11.8%

Losing years: 2000 (-36.9%), 2001 (-17.8%), 2002 (-21.0%), 2005 (-8.9%), 2008 (-45.1%), 2011 (-4.1%), 2014 (-6.3%), 2015 (-9.2%), 2016 (-15.4%), 2018 (-32.6%), 2022 (-27.1%), 2026 (-2.9%). Each cell: the strategy, then the benchmark below it. * a part year.

// THE IDEA, AS PUBLISHED

William O'Neil, 'How to Make Money in Stocks' (1988), base patterns · 1988

Prior uptrend of 30%+; cup of 7-65 weeks, rounded, typically 12-33% deep
Handle of 1-2+ weeks drifting down on light volume in the upper half of the base
Buy as price clears the handle high (pivot) on volume 40-50%+ above average, not more than 5% past it
Cut the loss at 7-8% below cost

RUN IT YOURSELF ▸ IN THE LIBRARY

A real computation on the QuantGPT warehouse, walk-forward. A study across the whole market includes only part of the companies that later delisted from 1998 (survivors only before); a study on your own list of tickers is not affected. Gross returns, no costs except where stated. Past performance is not a promise. Findings, not advice. COMPUTED 2026-11-09 20:55 ON THE QUANTGPT WAREHOUSE. COMPANIES THAT LATER DELISTED ARE ONLY PARTLY IN THIS UNIVERSE (A FIX IS IN PROGRESS), SO THE RESULT LEANS TOWARD SURVIVORS. FUNDAMENTALS BY FILING DATE. NOT INVESTMENT ADVICE. PRIVACY