Decoding the Crypto Buzz: A New Way to Spot Winners
The Rise and Fall of Cryptocurrencies
In the whirlwind world of cryptocurrencies in the course of the late 2010s and early 2020s, Tauhid Zaman witnessed a plethora of crypto coins making their grand entrance only to fade into thin air. These coins often had a temporary stint within the limelight, with some lucky individuals striking it wealthy, just for the joy to fade away swiftly.
Finding Patterns in Chaos
“As a scientist, I started to wonder if there was a pattern in all that noise,” says Zaman, an associate professor of operations at Yale SOM. “And I wondered if it was a financially predictable pattern.”
The key with these coins is that long-term investment is just not the goal. You catch the wave after which get out.
Listening to the Twitter Chatter
Teaming up with PhD student Khizar Qureshi, Zaman turned to Twitter to see how people were talking about these burgeoning coins. They discovered that by analyzing the conversation in the appropriate way, they may pinpoint which coins had the potential to thrive over the subsequent month.
“The key with these coins is that long-term investment is not the goal,” Zaman explains. “You catch the wave and then get out. This is the lesson for trading crypto in general.”
Creating the Engagement Coefficient
Zaman and Qureshi developed a novel method to distill the hype. Instead of just counting tweets, which Twitter limits, they crafted an “engagement coefficient.” This metric considers the follower count of accounts tweeting a few cryptocurrency, alongside the likes and retweets those tweets receive. This number, starting from zero to at least one, reflects how much chatter and a focus a coin is getting over a month. By applying this to 48 cryptocurrencies launched between 2019 and 2021, they simulated month-long investments achieving a hypothetical return of nearly 200%.
This gives you a technique to take the general temperature of a subject by sampling a comparatively small amount of information. With just a pair thousand tweets you possibly can have a look at a crypto coin, a movie, a brand new brand or product or politician.
Striking the Right Balance
“One of the really cool things was that this signal wasn’t monotonic,” Zaman notes. They observed that if the engagement coefficient for a coin was too low, it wasn’t price investing. Yet, if the coefficient ballooned, it indicated a possible pump-and-dump scheme, often driven by bots creating fake hype. The trick was to search out the Goldilocks zone where investment was ideal.
Beyond Cryptocurrencies
Interestingly, Zaman sees applications for this method beyond cryptocurrencies. He tested it in his social media class to predict movie success. Students gathered buzz data on several movies, and sure enough, the Super Mario Bros. Movie, which had essentially the most buzz, became the top-grossing film of 2023.
“This gives you a way to take the overall temperature of a topic by sampling a relatively small amount of data, and it seems to predict success really well,” he says. “With just a couple thousand tweets you can look at a crypto coin, or a movie, perhaps a new brand or product or politician.”
Image Credit: insights.som.yale.edu
