Catching the Wave: Inside Our Retail Momentum Screener
- Zackary
- May 29
- 13 min read
It all started with a simple question we asked ourselves: How could we have spotted high-momentum stocks before they took off? That question became the foundation for the Retail Momentum Screener—a tool designed to detect early signs of retail-driven momentum before they become obvious to the broader market.
One common trait among many momentum stocks is the level of interest they attract from retail investors. While retail activity represents only a small fraction of total market capital, when it’s concentrated on the right emerging names, it can be powerful enough to ignite a price surge—often one that institutions then try to ride themselves. What’s interesting about retail momentum is that it tends to build in waves. It often starts with early adopters—those first few investors who spot something intriguing. Then come the first followers, and as the story spreads through social channels, trading forums, and watchlists, it can grow into a full-blown retail love affair (I can’t stop thinking of this old instructional video while writing these lines—it kind of illustrates what retail momentum feels like to me.). This kind of momentum has a more predictable, organic buildup compared to institutional money, which often moves in after a catalyst like an earnings surprise and does so in large, sudden blocks. Retail momentum, by contrast, can be tracked as it gains traction—making it possible to detect the wave before it crests.
The screener is built to capture these moments by identifying unusual spikes in attention—the kind that often mark the beginning of strong upward moves. In hindsight, this approach flagged early signals in names like Affirm (AFRM), Upstart (UPST), and GameStop (GME), and even surfaced promising setups during development in names like AppLovin (APP), Palantir (PLTR), and Vistra (VST).
This kind of analysis only became possible after the GameStop saga of 2021, when institutions were forced to recognize the sheer influence of coordinated retail behavior. It was a turning point: a wake-up call that led data providers to start building tools specifically aimed at tracking retail flows. That shift opened the door to new types of signals—ones focused not on fundamentals or institutional order flow, but on where the crowd is gathering, often before the market fully catches on.
And this retail momentum—capable of delivering considerable gains—is not just an anecdotal theory built around the unusual story of GME. Let’s be honest: the GME saga was so unique they made a movie about it. But as we dug into retail data, it quickly became clear that momentum picking up speed within the retail segment is far from a one-off. It’s a consistent and measurable pattern.
Indeed, the average maximal gain over a one-year period across all runs flagged by our Retail Momentum Screener is 51.05%, with a median of 27.35%. That’s not just a handful of lucky spikes—it reflects a broad, repeatable structure. Even more telling, 77.70% of all runs reached at least +10% during the year following the signal.
To put that in perspective, even in a strong year like 2023, only about 60% of S&P 500 stocks ended with a positive return—and the broader NYSE and Nasdaq posted similar numbers. That means 40% of stocks still lost value, despite a bullish market backdrop. (And it’s worth noting: our Retail Momentum dataset includes the difficult 2022 bear market.)
The takeaway is simple: consistent outperformance is rare. But tracking retail-driven momentum has helped us isolate a corner of the market where the odds are materially better—and that’s not just a theory. It’s what the data shows.
The following sections will dive into how the screener works under the hood to help you gain an understanding of what it is and how to use it.
We Start With the Right Universe
To keep results meaningful, the screener starts by filtering the list of stocks. It only looks at tickers that meet both of the following rules:
Listed on NASDAQ Global Market, NASDAQ Global Select, NYSE, or NYSE ARCA
Market capitalization under 50 billion dollars
This helps focus the analysis on companies where retail investors are more likely to have an impact. Mega-cap stocks are less likely to move based on retail attention alone which made the signal less useful. Inversely, the really small caps (or Penny Stocks), traded on the NASDAQ Capital Market for example, flag too often making it hard to be actionable. Even more so that we have found those to be highly unreliable either going on a run of over 2000% or going down to almost 0% with almost 50-50 odds. This made this part of the tool more aquainted to gambling which we do not like. We want to enter trades with the odds in our favor which led to us discarding those stocks.
What Is a "Run"?
The screener works by detecting flags on specific stocks. These flags are signals that suggest a surge of retail interest. But instead of looking at each flag individually, we group them into what we call a run.
A run is a sequence of consecutive flags on the same ticker, as long as no more than 100 calendar days pass between them. It does not define a price movement but rather a pattern of consistent retail signals over time. The difference is subtle, but important. The aim of grouping flags in a run is not to time the price action movement. The aim was to address two main issues:
When the screener flags multiple times on the same stock in a good run, we could have counted each flag as a success. This however made the statistics skewed toward a higher success rate since the same run was counted more than once.
Inversely, we often saw one final flag near the top—inevitably adding a “bad” trade to our stats. But that’s to be expected: any strong move up will eventually stall or consolidate. The real question is, was it really a bad trade if the screener had already flagged multiple opportunities earlier in the run?
Philosophically, once the first flag appears, the screener has already done its job: the stock is now on our radar. While repeat flags are still useful—they help us gauge the persistence of retail interest—they don’t carry the same weight as that initial signal. Take the recent example of D-Wave (QBTS), a leader in the quantum computing space. Since November 22nd, the Retail Momentum Screener has flagged it 24 times, never going more than 100 days without a new signal. Notably, flags appeared near both the late December and late March peaks. If we treated those late-stage flags the same as the first one, we might have been tempted to chase the trade. But context matters: a dense cluster of recent flags often signals overheating, even if the price continues to climb for a while—as it did with QBTS throughout December.

In short, the concept of a run allows us to study how long a retail-driven story lasts and how it evolves, rather than treating every flag as a separate event.
Not all runs are equal
Although we made sure the screener captured all the strong runs we’ve observed in recent history, it was never realistic to expect it to flag only winners with 100% accuracy. We tested countless methods to filter out the weaker signals—and while some worked in isolated cases, there was always a counterexample: a strong run that would’ve been filtered out by the same logic. That’s not surprising, since retail momentum is just one of many forces that shape a stock’s trajectory.
That said, we still reached a success rate that genuinely impressed us. One thing that helped was grouping individual flags into broader momentum runs—since poor signals were often not the first to appear. Still, there are cases where a flag was followed by a price peak that wasn’t reached again for over a year. It’s part of the risk that comes with this kind of signal-based strategy.
To address this issue without filtering out potential winners, we chose to keep certain filters—but only as warnings. Each flagged run can include one or more warnings, depending on the stock’s profile at the time:
Small Cap
(Displayed with a red circle containing an exclamation mark)
This flag appears when the stock’s market cap is under $800 million. While small caps have a success rate similar to larger stocks, their volatility is significantly higher. These names can deliver spectacular gains—or painful losses. We decided to highlight them not because they should be avoided, but because they may not align with the investing style we—or most of our members—tend to favor.
Volatile Move
(Displayed with a yellow triangle containing an exclamation mark)
This warning is triggered when the stock has already moved sharply in the short term, either up or down. In such cases, the risk of the stock being overbought is elevated, so the flag is simply a prompt to proceed with a bit more caution.
Low Volatility Sector
(Displayed with a pale blue snowflake)
This flag appears when the stock belongs to a sector that historically shows less dramatic price moves. Our sector-level analysis of Retail Momentum Screener results (across categories like Tech, Industrials, Healthcare, etc.) revealed clear differences in behavior. Tech stocks, as expected, led the pack—consistent with retail investor preferences. Some sectors sit not far behind or in the middle, but others consistently underperform in momentum setups. This flag is used sparingly and only appears when the stock is in one of those least reactive sectors, helping to set more realistic expectations.

These warnings help put the signal in context. Not every retail surge is worth chasing, and some situations come with higher risk or lower odds of success.
Measuring the Outcomes
To extract the screener’s performance statistics, we used an approach designed to reflect the best-case potential of each run. This was a deliberate choice—introducing a full strategy with defined entries and exits would have blurred the line between “was the flag meaningful?” and “did we trade it well?”. Our goal was to assess the quality of the signal itself, independent of execution.
Once a stock is flagged, TuneMap—or your preferred strategy—can be used to decide how to act on it. But for the purpose of evaluating the screener alone, here’s the method we used:
Entry: We assumed an entry at the open on the day following the first flag in a run, since the data used to generate the flag isn’t available until the next morning—making that the earliest possible entry point.
Exit: We measured the exit as the highest closing price within a selected period (ranging from 1 to 12 months), representing the maximum potential of the run—assuming you had the timing of a legendary trader.
This method captures the maximum potential gain, assuming the investor managed the position well. While a stock could see an even larger intraday move—especially since high-momentum names often peak dramatically—we chose to focus on closing prices to keep the analysis more realistic. Most trading and holding strategies operate on daily timeframes, so using closing prices better reflects how investors typically engage with these signals.
In some cases, the maximum closing price may still result in a loss—especially if the entry happened near the peak of the run. That’s why it’s important to clarify: these statistics do not represent the average return we expect from trades taken using the screener. Instead, they reflect the best-case outcome that a savvy investor might aim for. Still, this approach offers the clearest lens for evaluating the screener’s potential—it tells us whether there was meaningful opportunity in the flagged run, and how significant that opportunity might have been.
Beyond that, dissecting these stats helps build realistic expectations. Not every flagged stock leads to a major rally. Many produce modest gains, and some result in losses. That’s why reviewing the numbers is key. The screener’s goal is to surface early signs of retail-driven momentum—but it’s up to the investor to assess each opportunity with care. That includes understanding the business behind the move, the broader context, and putting a risk management plan in place. We previously discussed using ATR and trailing stop-loss strategies to manage risk, but you can also use TuneMap and your preferred technical indicators to guide your decisions.
The first statistic we looked at is the proportion of flagged runs that reach a certain maximum gain (in %) within a fixed period after the initial signal. The chart below shows these results over a 6-month window.
The blue line represents the percentage of runs that, at some point during the six months, achieved at least one closing price above the entry point. Impressively, 91.7% of flagged runs met that minimal threshold—suggesting that most signals do result in some upward movement. However, this is a low bar to clear, which is why we extended the analysis to include higher return thresholds.

The same blue line shows that:
44% of runs reached at least +20% at some point within six months.
Only 5.2% of runs reached gains exceeding +100%.
These numbers help illustrate both the strength and the limits of retail-driven momentum: while most runs see some gain, only a minority go on to deliver outsized returns.
The grey boxes beneath the blue line represent the proportion of runs that fall exactly within each gain range. This complements the cumulative view from the blue line, which includes any run that surpassed a given threshold (e.g., a run that reached +40% is also counted in the 0%, 10%, 20%, and 30% point on the blue line). The grey boxes, by contrast, isolate runs whose maximum gain falls strictly within each range—based on the width of the bar. For example, roughly 25% of all runs had a maximum gain between 0% and 10% during the observed period.
This breakdown becomes especially useful when comparing different timeframes. In the next two charts, we compare results for a 1-month period and a 1-year period following the first flag.
The difference is striking.
In the 1-month chart, only 80% of runs manage a close above the entry price, and 50% of all runs reach a maximum gain of just 0% to 10%.
In the 1-year chart, that proportion climbs to 94.5% above the entry price, and the percentage of runs with a maximum gain in the 0% to 10% range drops to just 16.8%.
This suggests that retail-driven momentum often takes time to play out—and that the biggest moves tend to happen months after the initial flag, rather than immediately.


Another key set of stats we like to examine are the average and median gains over different time periods. We report both because the dataset includes a few extreme outliers—like GME’s legendary +4,647% run in 2021—which can distort the average and make it less representative of typical outcomes. That’s where the median becomes especially useful. It gives a clearer sense of what a typical run looks like. For the 12-month period following a flag, the median gain is 27.35%, which means that half of all flagged runs reached at least that level at some point during the year.

One important caveat is that the peak of each run can occur at very different times. Some runs spike early and then fade into losses, while others may start with a small dip before eventually rallying. As we’ve mentioned before, retail momentum is just one of many forces influencing a stock’s path. Company-specific news, macro conditions, or a shift in investor sentiment can abruptly end a move.
A good example is Upstart (UPST). Its epic run came to a halt at the end of 2021 when inflation concerns and the Fed’s clear intention to raise rates shifted the market environment. Despite seeing pockets of renewed momentum since, the stock has yet to fully recover from that turning point.
Diving in the interface
The last part of this blog post is about the interface and how to use the Retail Momentum Screener. The interface is split into 4 sections each adressing a specific feature.
The top left section is the main one, showcasing all the active runs, ordered by the most recent flag. This means that any new flags from the day will appear at the top of the list, while all runs still within 100 days of their latest flag will be displayed further down.

Each morning around 7 AM, new entries should appear at the top. If a stock has already been flagged before, the “Count” value will be updated along with the “Latest Flag” date. If it’s a brand-new flag, a new row is added, with the “Start” and “Latest Flag” dates being the same.
The “Gain” and “Max Gain” columns represent the percent return from the open price after the Start date, using the most recent close and the highest close to date, respectively. These values are updated one day after the initial flag, as they require at least the next-day open and close to be calculated. You will see "0.00%" values during the first day following the flag as is the case in the first rows in the screenshot.
The “Warning” column shows icons described in Section 3, which highlight certain conditions or risks associated with the run.
The top right section contains interactive charts showing the performance statistics discussed in Section 4. We felt it was important to keep these nearby, since the odds shown there help frame our level of confidence in any new flagged runs. It also allows for a quick visual comparison—showing whether a current run is still in its early stages or has already outperformed historical averages.
The bottom left and bottom right sections are focused on a specific ticker. By default, they load the first stock in the “Latest Flags” table. The chart displays all past flags for that stock, and the table next to it summarizes them as grouped runs. This view allows users to explore how the screener has performed on that specific name in the past—and to see whether the stock has previously attracted retail interest or if this is the first time it’s being flagged.
Final Words
What started as a simple research project driven by curiosity turned into something much more: the Retail Momentum Screener. It’s become a surprisingly powerful way to spot early signs of momentum fueled by what we like to call a Retail Love Story.
We’ll definitely be using it in our own trades—but not by blindly jumping on every flag that pops up each morning. That’s not the game we play. The screener might highlight strong statistical odds, but we’re not momentum chasers by default. We’ll stay true to who we are as investors: focused on sectors we understand, like tech, and drawn to stories that feel robust and aligned with our convictions. And, we’ll take the time to validate each signal using our Stock Health Dashboard and map out a solid plan with TuneMap. That way, we can hold positions with more confidence and clarity.
From what we’ve seen, the biggest runs don’t happen overnight—even if they unfold quickly once they start. When a ticker gets flagged, it’s often just the beginning of the story. That gives us time to dig deeper—observe how the stock is being discussed online and in the media—before taking a position. Retail love stories usually build gradually, with momentum showing up more than once before a true breakout.
While working on the dataset, we also noticed a strong correlation between the most beloved retail names and how strongly they rebound after market corrections. Just look at how APP and PLTR have already nearly doubled from their April lows. This pattern has held true for nearly every top retail-driven stock over the past decade. That’s why, in a future update, we plan to dynamically integrate these high-conviction names into our Downtrend Exhaustion Dashboard—so we can better capture and act on this powerful behavior. Even before that’s live, though, these early findings already show the value of tracking where retail is putting its money.
We hope you enjoy using this tool as much as we do and that it helps you uncover some great opportunities along the way.
I am also quite interested in how much WU will share about the positions it takes - please let us know. I suspect the User Forum will be a valuable place where users will share insights about the signals they are acting on, their risk management strategies, etc. I can't wait!!
Thanks Zack! Will WU alert and analyze the trades they take?