Strategy pattern · Mean reversion
Test a short-term reversal strategy with costs counted from day one.
Super Algo Kit grades the short-term reversal strategy B: buy last week's biggest losers, sell the biggest winners, hold for a week. The effect is well documented, but its result after costs is disputed and has faded for large, liquid stocks. The kit tests your version with next-open fills, full costs and a paper run before any live step.
strategy facts
Short-term reversal: fading last week's extreme movers
- Family
- Mean reversion, from published literature
- Markets
- Equities and ETFs
- Timeframes
- Daily and weekly bars; a one-week hold, then rebalance
- Evidence grade
- B: well documented, yet the after-cost result is disputed and has faded among large, liquid stocks
- Status
- Literature: described in published research, not yet tested by the kit
- Data needed
- Daily prices or quote midpoints, a point-in-time universe with delistings, earnings dates, borrow fees and costs
- Fragility test
- The kit reports the break-even cost multiple; below 2 it treats the idea as fragile
From the kit's own card. Not investment advice.
Paper first
Test it before you trade it.
Super Algo Kit runs inside the coding agent you already use. It interviews you, writes the spec with pass marks set first, then builds, backtests and paper-tests. Real money starts only when you type the authorize command.
The plan, step by step
Tick them off as you go.
How does the short-term reversal strategy work?
Over a week to a month, stocks that moved most against their peers have tended to give part of the move back. A leading explanation is liquidity: traders in a hurry push prices away from fair value, and the patient side is rewarded for absorbing their orders.
That reward tends to grow when liquidity is scarce, as in volatile markets. Part of what shows up in closing prices is simply bid-ask bounce, and no trade can capture that.
Short-term reversal rules in plain words
Here is a summary of the card's sketch. Each choice of look-back, hold and universe is a trial.
- Start from liquid stocks, chosen as they were on each date.
- Rank each stock's past-week or past-month return against the rest.
- Buy the biggest losers and short the biggest winners, or run long only, equally weighted.
- Hold for one week, then rebalance.
- Set aside moves driven by earnings or other scheduled news, which tend to continue.
Why short-term reversal often fails after costs
Turnover is heavy, and beyond the most liquid stocks the costs often outweigh the raw effect. A backtest that decides on the close and fills at that same close books a spread you could never get.
The strategy supplies liquidity exactly when it is dearest to supply. So its losses tend to bunch together in stressed markets.
How Super Algo Kit tests a reversal bot before any money
Fills come at the next open or the midpoint, never at the signal close, and leakage checks enforce it. Costs, taxes and borrow fees come from the market pack's cost model.
The kit reports the break-even cost multiple: how far costs could rise before the effect disappears. Below 2, the idea counts as fragile. Results are split by volatility regime, where both the reward and the risk are expected to rise.
Before you rely on it
Where it fails.
- High weekly turnover: beyond the most liquid stocks, costs often swallow the whole effect.
- Bid-ask bounce: deciding and filling at the same close captures a spread that is not available.
- Moves driven by news tend to keep going rather than snap back.
- Losses cluster in stressed markets, when liquidity is most expensive to supply.
- Short-selling limits and borrow recalls.
FAQ
Short-term reversal: questions.
Does the short-term reversal strategy still work?
Super Algo Kit makes no promise that it does. The kit grades it B: the effect is well documented. Its result after costs is disputed, and smaller than it was for large, liquid stocks. Your version must clear pass marks you set before the first test.
What is bid-ask bounce in a reversal backtest?
Closing prices jump between the bid and the ask, which looks like reversal but cannot be traded. A backtest that decides and fills at the same close counts that spread as a gain. Super Algo Kit fills at the next open or the midpoint instead.
Is short-term reversal the same as mean reversion?
It is one kind of mean reversion, measured across stocks over a week or a month. The kit keeps intraday fades around VWAP on a separate card, graded C. Both cards list where they fail and how the kit tests them.
Can I run short-term reversal long only?
Yes, the card allows a long-only version that buys the biggest losers. That avoids short-selling limits and borrow recalls. It still trades every week, so costs remain the main test.
Can Super Algo Kit build a short-term reversal bot?
Super Algo Kit helps your own AI coding agent build one as real code in your project. It interviews you, writes a strategy card and spec, backtests with costs and runs a paper test. Live trading starts only when you type the authorize command.
Keep reading
More guides.
United States · Broker APIAlpacaSuper Algo Kit helps you build an Alpaca trading bot inside your own AI coding agent.
United States · Broker APIInteractive BrokersSuper Algo Kit helps you build an Interactive Brokers trading bot inside your own AI coding agent.Claude Code · Coding agentClaude CodeSuper Algo Kit turns Claude Code into an algo trading team, so you can build your own Claude Code trading bot.Sources the kit's card cites
- Jegadeesh (1990). Evidence of Predictable Behavior of Security Returns. Journal of Finance.
- Lehmann (1990). Fads, Martingales, and Market Efficiency. Quarterly Journal of Economics.
- Nagel (2012). Evaporating Liquidity. Review of Financial Studies.
Build it with Super Algo Kit.
15 specialist roles and 35 skills inside your coding agent. Paper first, live only when you say.
Super Algo Kit is development software. It is not investment advice, a signal service or a promise of performance. Trading involves substantial risk, including the loss of all capital you trade with.