The Quality Momentum Portfolio

A rules-based two-factor strategy. First a hard quality minimum removes every company that is not actually profitable — positive operating margin and positive return on assets, with missing data treated as a fail, never a pass; then the survivors are ranked by residual momentum — 12-month price momentum with the most recent month skipped, measured net of each stock’s beta to the market. Hold the top 25 equal-weight, re-rank monthly: a stock enters at rank 25 or better and stays while it still ranks in the top 60, with at most 7 of the 25 from one industry. No forecasts, no discretion. Tested point-in-time back to 2009 against both the S&P 500 and the Nasdaq-100 — the honest caveats are shown right next to the results.

How the strategy is computed

Every month-end, using only data knowable at that date (annual filings with a 91-day lag, plus that day’s price):
  • Hard quality minimum — a company qualifies only if it is genuinely profitable: positive operating margin AND positive return on assets in its latest annual filing. A company with missing data fails — no data, no entry. This deliberately excludes pre-revenue and story stocks regardless of how strong their price momentum is.
  • Residual momentum — rank the survivors by their 12-month-minus-1-month price return net of market beta (the stock-specific momentum, not the part that just moved with the market).
  • Hold 25 names equal-weight; re-rank at the next month-end under a rank band: a stock enters at rank 25 or better and is kept while it still ranks in the top 60 — only when it drops below 60 (or fails the quality or tradability gate) is it sold and the slot given to the best-ranked entrant. A full monthly re-rank had been selling winners on rank noise; the band halves turnover. Risk cap: at most 7 of the 25 from any one industry (Fama-French 12 industries, from each company’s SIC code in its SEC filings). Universe: US stocks ≥ $1B market cap at the rebalance date, with a point-in-time tradability floor — a median daily dollar volume of at least $5M over the three complete months before the rebalance (a name that barely trades cannot be bought at the modelled cost, so it does not belong in the test or the basket). Returns are price-only (dividends excluded on both sides).
  • Revision note (September 2026): the rank band and the industry cap replaced a plain monthly re-rank. They were two of five holding rules tested together on the same data (with a return-consistency screen, an intermediate 12-7 month signal and staggered tranches, all rejected); they were the only two that improved every test window. Under the previous rule this page showed 20.3%/yr after costs for 2009–2026 (a tie with the Nasdaq-100) and 10.7% for 2012–2016 (behind the S&P 500). We keep those numbers here on purpose: the change was made after seeing them, which is itself a form of selection, and the true out-of-sample test of the new rule only starts now.
🔒

The 25 holdings are for Premium members

The full performance and backtest below are free for everyone. Premium unlocks this month’s 25 positions with live tenure, updated automatically at every month-end rebalance — $19/month or $149/year, with a 14-day free trial.

Start 14-day free trial
Already a member? Sign in

The backtest — full period and three independent windows

Same rules applied point-in-time. The 2012-2016 and 2009-2012 windows were run after the strategy was designed on 2016-2026 data — a genuine out-of-sample check. Benchmarked against the S&P 500 (SPY) and the Nasdaq-100 (QQQ).

The chart shows total return since the selected period started, after 0.3%/trade costs on the strategy side — the strategy (green) against the S&P 500 (SPY, grey) and the Nasdaq-100 (QQQ, purple). The CAGR figures are that same result as a constant annual rate; the % scale on the chart isn’t directly comparable to the yearly stats. Switch the tabs for the full run or each window.

Honest limitations — read before drawing any conclusion

Educational purposes only — not investment advice. The Quality Momentum Portfolio is a rules-based research strategy, not a recommendation to buy or sell any security.

All performance shown is hypothetical and backtested — computed by applying the rules to historical data, not achieved with real money. Backtests have inherent limitations: they benefit from hindsight; may not capture all real-world costs, taxes or slippage; and survivorship bias is handled head-on rather than footnoted: the test universe includes companies that later delisted or went bankrupt, restored from the full SEC delisting catalog (Form 25, 6,300+ dead filers) with their real filed fundamentals — dead positions exit at their last traded price. Two technical limitations remain for that cohort: the liquidity floor cannot be applied to delisted names (no volume history survives; including them without it can only add losers), and their split adjustments are restored heuristically, cross-checked against filed share counts (details). Results starting near the 2009 market bottom are flattered by that entry point, and the strategy was selected after testing many variants, so part of the historical edge is the luck of that selection.

Past performance — real or hypothetical — does not guarantee future results. This strategy is concentrated (25 stocks), more volatile than a broad index, with historical drawdowns approaching 40% in this test (worst −37%, before costs), and momentum strategies as a class are known to suffer sharp reversals — especially after crash rebounds — during which they can trail the index badly for extended stretches. You may lose money. Nothing here is personalized advice — consult a licensed financial adviser before investing. The Compound Family is not a registered investment adviser.