Sell in May and go away on SPY — Published Backtest & Verdict

We tested it in public: Sell in May and go away on SPY (2019-01-02 to 2026-10-14) returned +53.7% vs +244.7% buy-and-hold across 7 trades. Exact rules, full stats, and our honest verdict.

• Total return: +53.7% (trailed buy-and-hold at +244.7%)
• CAGR: +5.7% vs +17.2% buy-and-hold
• Max drawdown: -33.7% vs -33.7% buy-and-hold
• Win rate: 57.1% over 7 trades
• Period: 2019-01-02 to 2026-10-14 (SPY), published 2026-10-15

The claim on trial

“Sell in May and go away” — stocks stall from May to October, so sit those months out in cash.

The exact rules

• Entry: buy SPY at the close of the LAST trading day of October.
• Exit: sell at the close of the LAST trading day of the following April.
• Cash earns 0% May–Oct. Long only, fully invested while in.
• Entry on bar i starts earning on bar i+1 (no look-ahead); exit on bar i retains bar i's return — same convention as the weekly series.
• No transaction costs, no taxes modeled (disclosed in thread + companion).
• Backtest starts in cash 2019-01-02; first entry 2019-10-31 (the Nov 2018 entry predates the data window — no partial 2019 season fabricated). Buy-and-hold computed over the identical window from the same data.

Our honest verdict

BUSTED. The rule gave up roughly four-fifths of the market's return (+53.7% vs +244.7%) for zero drawdown protection: the period's worst crash (Feb-Mar 2020, -33.7%) landed inside the invested Nov-Apr window, so both drawdowns are identical. $10,000 became $15,369 following the rule vs $34,472 buy-and-hold.

Original X thread · StratIQ track record · All published backtests

Charted on TradingView (affiliate link — we may earn a commission at no extra cost to you): tradingview.com

Not financial advice — research and education only; do your own due diligence.