// STUDY RESULT · 1998-01 TO 2026-09

Inspired by Jegadeesh and Lehmann: Short-Horizon Reversal

NO EDGE

At the 1-week to 1-month horizon, returns reverse: last period's losers beat last period's winners. Later work links the effect to liquidity provision.

How this run differs from the source: Buys the 20 worst one-month losers, long only; the papers test reversal as a long-short spread, Lehmann's weekly.

	THE STRATEGY	$SPXTR BUY & HOLD
CAGR	-1.9%	9.3%
Sharpe ratio	0.17	0.66
Max drawdown	-81.1%	-50.9%

// GROWTH OF $1, LOG SCALE

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

Out-of-sample (from the split): CAGR -2.7% against 14.0% for the benchmark; Sharpe 0.20 in-sample, 0.13 out-of-sample.

After 25 bps of trading costs: -7.4% a year. BELOW RANDOM

// DECADE BY DECADE

ERA	STRATEGY	BENCHMARK
1990s	7.1%	20.9%
2000s	-2.8%	-0.8%
2010s	5.2%	14.0%
2020s	-12.5%	15.2%

// YEAR BY YEAR, LOSING YEARS IN RED

1998*-22.2%27.2%

199948.9%21.0%

2000-51.6%-9.1%

200157.2%-11.9%

2002-27.2%-22.1%

200334.1%28.7%

200432.3%10.9%

2005-21.5%4.9%

200621.3%15.8%

2007-8.2%5.5%

2008-61.9%-37.0%

2009139.1%26.5%

201037.7%15.1%

2011-29.7%2.1%

201234.4%16.0%

20139.5%32.4%

2014-32.7%13.7%

20155.6%1.4%

201645.0%12.0%

20170.5%21.8%

2018-0.6%-4.4%

201917.7%31.5%

202017.9%18.4%

20218.3%28.7%

2022-38.5%-18.1%

2023-3.1%26.3%

2024-33.1%25.0%

2025-24.5%17.9%

2026*-3.6%11.8%

Losing years: 1998 (-22.2%), 2000 (-51.6%), 2002 (-27.2%), 2005 (-21.5%), 2007 (-8.2%), 2008 (-61.9%), 2011 (-29.7%), 2014 (-32.7%), 2018 (-0.6%), 2022 (-38.5%), 2023 (-3.1%), 2024 (-33.1%), 2025 (-24.5%), 2026 (-3.6%). Each cell: the strategy, then the benchmark below it. * a part year.

// THE IDEA, AS PUBLISHED

Jegadeesh (1990); Lehmann (1990) · 1990

Jegadeesh: rank on predicted monthly return (dominated by a negative one-month lag), long top decile, short bottom
Lehmann: weekly, weights proportional to minus each stock's prior-week return relative to the market
Hold one month (Jegadeesh) or one week (Lehmann); costs decide implementability

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 2026-11-07 16:19 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