Residual momentum
Rank winners versus losers on a lookback window; works until crowding, reversals, or a regime shift punishes trend followers.
Overview
Residual momentum sits in the Stocks chapter of the systematic catalog. On QUSXFI we treat it as a testable hypothesis: specify entries, exits, sizing, and costs—then ask whether edge survives out-of-sample scrutiny.
Discretionary traders often arrive at similar ideas intuitively; the quantitative version forces you to write the rule before you see the next bar. That discipline is what makes results reproducible—or exposes them as luck.
Based on the research catalog 151 Trading Strategies (Kakushadze & Serur, 2018), section 3.7. Educational summary—not a replication of the full formal definition.
Signal and Portfolio Construction
Residual momentum ranks past winners and losers over a declared lookback, then tilts the book toward persistence.
Map every input Residual momentum needs in Stocks—prices, vol surfaces, fundamentals, or legal milestones—and verify point-in-time integrity.
Implementation and Research Process
Run Residual momentum with and without vol scaling; report turnover and capacity at 5% and 10% of ADV participation.
Slice Residual momentum by vol regime and rate cycle—momentum is conditional, not universal.
Walk-forward or hold-out test Residual momentum; report turnover, max drawdown, and exposure—not CAGR alone.
Risk: What Breaks This Strategy
Momentum crashes—sharp reversals after crowded trends—are the signature tail risk of Residual momentum. Factor crowding and ETF flows accelerate the unwind.
Turnover and transaction costs scale with rebalance frequency; what worked gross of fees dies net.
Regime shifts (policy shocks, bear markets) can flip sign on the same lookback parameter that looked brilliant in the prior decade.
Common Mistakes to Avoid
- Erasing losing Residual momentum months instead of documenting regime breaks—that is how research firms stop learning.
- Reporting Residual momentum backtests without fees, slippage, and realistic fill rules.
- Ignoring transaction costs on Residual momentum full-universe rebalances.
- Optimizing Residual momentum lookback on the same sample you report as final.
How to Study This Strategy
- Run Residual momentum walk-forward on a liquid universe; export turnover and sector exposures.
- Write Residual momentum failure triggers: drawdown, turnover spike, sign flip on the signal.
- Codify Residual momentum signal, lag, rebalance, and vol-scaling rules without discretionary overrides.
- Identify the worst momentum crash month for Residual momentum in-sample and replay it out-of-sample.
- Simulate Residual momentum at two participation rates; note where capacity binds.
Key Takeaways
- Residual momentum ranks past winners and losers—edge is conditional on trend persistence, not guaranteed by the lookback.
- Rebalance frequency and universe for Residual momentum drive turnover; gross returns without fees mislead.
- Sector neutrality changes whether you trade pure trend or a constrained factor portfolio.
- Regime shifts can flip sign on the same parameter that worked in the prior decade.
- Walk-forward Residual momentum; a single in-sample lookback winner is a research accident until confirmed out-of-sample.
Learning Tip
Plot Residual momentum cumulative return with crash months highlighted in red—stakeholders remember color, not Sharpe.
Explore related strategies in the sidebar or return to the full catalog.