Momentum
The momentum strategy
In plain words
Stocks that rose the most over the past year tend to keep outperforming the others for a few months. The momentum strategy buys these winners, sells the losers and lets the trend do the work.
A momentum signal, number by number
This is what a momentum signal looks like in PairScanner. The stock and the figures are fictional.
Click a number to learn its role
Expected move+4.8%over 60 sessions, after costs
My role: tell you what this kind of signal earned on average in the past, once costs are paid. Here +4.8% over 60 sessions, comfortably enough to cover round-trip costs.
80% range-3.2% to +12.6%median +4.1%
My role: show the range of the most common outcomes. Eight similar signals out of ten ended inside it. The narrower it is, the more predictable the outcome.
Probability63%of a positive outcome
My role: estimate the chance that this signal ends positive, after costs. 50% would be a coin flip; 63% means about two similar signals out of three ended positive.
Sample214 / 340positive cases, 2019 to 2026
My role: tell you how many past situations the figures rest on. 340 cases make a solid base: the figures do not hang on a few lucky trades.
Worst decile-7.4%one outcome in ten did worse
My role: give the size of an unfavorable outcome, so you can size the position knowingly.
ValiditySep 29, 2026expires Dec 22, 2026
My role: date the data used and tell you how long the signal counts. An expired signal is no longer tracked.
What PairScanner does
PairScanner applies this rule automatically. Once a month, the algorithm measures the performance of every stock in its universe of liquid US stocks over the last twelve months, excluding the most recent one, ranks them and keeps the strongest and the weakest decile.
Every evening after the US close, it updates open signals and computes, for 20 and 60 session horizons, the expected move after costs, the estimated probability of a positive outcome, the range of plausible results and the size of a bad outcome. These figures come from replaying the same rule on history: they are past frequencies, not promises.
A variant applies the same idea to the nine major US sectors through their ETFs: the algorithm compares their performance over the same period and flags the strongest and the weakest sector.
You code nothing and calculate nothing: you open the Momentum tab of the dashboard and read today's result.
The idea in detail
Momentum is one of the best documented patterns in markets. The rule has three steps. Every month, measure each stock's performance over the last twelve months, leaving out the most recent month. Rank the stocks from the strongest to the weakest. Buy the top group, often the strongest 10%, and sell short the bottom group.
Positions are held for a few weeks to a few months, then the ranking starts again.
Why leave out the last month? Over one month the opposite effect dominates: stocks that just moved a lot tend to give some of it back. That is short-term reversal. Measuring over twelve months minus the last one, written “12-1”, separates the two effects.
A worked example
Take eight fictional stocks. Keep the strongest quarter and the weakest quarter: two bought, two sold. The real strategy ranks hundreds of stocks and keeps groups of 10%.
| Stock | 12-1 month performance | Rank | Decision |
|---|---|---|---|
| A | +64% | 1 | Bought |
| B | +41% | 2 | Bought |
| C | +23% | 3 | Ignored |
| D | +9% | 4 | Ignored |
| E | +2% | 5 | Ignored |
| F | -6% | 6 | Ignored |
| G | -18% | 7 | Sold |
| H | -31% | 8 | Sold |
Suppose that over the next month A and B gain 3% on average and G and H lose 1% on average. The long side gains 3%, the short side gains 1% since the stocks sold went down. Across the capital committed on both sides, that is about 2%, before costs.
Fictional example for teaching purposes. It is neither a signal nor a recommendation.
Why it would work
In 1993, Narasimhan Jegadeesh and Sheridan Titman showed that on US stocks from 1965 to 1989, buying the winners of the past 3 to 12 months and selling the losers earned on average about 1% per month over the following months, before costs.
The most common explanation is behavioral. Investors underreact to news: good news is built into the price only gradually, which creates a trend. Herding and fashion then extend the move.
Part of the effect comes from sectors: in 1999, Tobias Moskowitz and Mark Grinblatt showed that winning industries also tend to keep winning. That is the idea behind the sector variant.
What research says today
Momentum has been found in many markets and asset classes, stocks, bonds, currencies and commodities, as Clifford Asness, Tobias Moskowitz and Lasse Pedersen documented in 2013.
Christopher Geczy and Mikhail Samonov even observed it over more than two centuries of US market data, from 1801 to 2012. Few market patterns have been checked over such a long period.
Sources
Studies cited on this page:
- Narasimhan Jegadeesh and Sheridan Titman (1993). Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency. The Journal of Finance, 48(1), 65-91.
- Tobias J. Moskowitz and Mark Grinblatt (1999). Do Industries Explain Momentum?. The Journal of Finance, 54(4), 1249-1290.
- Clifford S. Asness, Tobias J. Moskowitz and Lasse Heje Pedersen (2013). Value and Momentum Everywhere. The Journal of Finance, 68(3), 929-985.
- Christopher C. Geczy and Mikhail Samonov (2016). Two Centuries of Price-Return Momentum. Financial Analysts Journal, 72(5), 32-56.
PairScanner promises no results: the figures describe what the strategies did in the past. Educational content, not investment advice; PairScanner places no orders.
See today's momentum signals