Twitter data can predict a rise in cryptocurrencies

[ad_1]

As cryptocurrency skyrocketed (and, ultimately, crashed) in the late 2010s and early 2020s, Tauhid Zaman saw countless cryptocurrencies appear and then disappear. There might be a few mentions on social media early on, maybe a brief flash in the public eye, a handful of people getting rich. And then poof, gone.

As a scientist, I began to wonder if there was a motive in all this noise, says Zaman, 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 not the goal. You catch the wave and get out.

He and PhD student Khizar Qureshi took to Twitter to monitor how people were talking about emerging coins. They found that if you measure the conversation correctly, it is possible to identify the coins with the best prospects over the next month.

The key with these coins is that long-term investing isn’t the goal, Zaman says. You catch the wave and get out. This is the lesson for crypto trading in general.

Zaman and Qureshi achieved their results by devising a new method to distill the hype. People have tried using the raw volume of tweets on a certain topic to predict results, assuming that many tweets imply strong future performance. But Twitter limits the amount of information that can be extracted from its site, which means that the raw volume is sometimes too large for anyone to obtain a meaningful sample; it is not possible to follow millions of tweets per month.

Researchers have alternatively looked at the predictive power of sentiment analysis: is the discussion around a given subject favorable? But insider shortcuts like #buythedip or #hodl, both of which convey positive sentiment in the crypto world, tend to elude machine learning analysis, as do memes expressing a sense of one way or another.

What Zaman did instead was develop an engagement coefficient based on the number of followers of accounts posting tweets mentioning a cryptocurrency as well as the number of times each tweet is liked and retweeted. These two metrics were combined to provide a single number between zero and one that indicated how many people were talking about and hearing about this cryptocurrency in a month. Zaman and Qureshi used this indicator to track a sample of mentions of 48 cryptocurrencies that hit the market between 2019 and 2021, and to make hypothetical one-month investments. These investments yielded a (hypothetical) return of almost 200%.

This gives you a way to take a subject’s overall temperature by sampling a relatively small amount of data. With just a few thousand tweets, you can watch a cryptocurrency, a movie, a new brand or a new product or a politician.

One of the really cool things was that this signal wasn’t monotonous, Zaman says. The researchers found, unsurprisingly, that if the engagement coefficient of a given coin remains below a certain threshold, it is not worth buying that coin. But too much buzz is also a bad sign, he adds: if the engagement coefficient got really huge, you also wanted to avoid buying the coin. Very high coefficients seemed to suggest that many bots were engaging with the coin and a potential pump and dump scam in which people artificially inflate buyers’ interest before the coin collapses. There was, he said, a place in Goldilocks where the investment made sense.

This idea, Zaman notes, could be useful to regulators trying to curb fraud. If soon after a coin is listed on a crypto exchange, it begins to create an unusually large buzz, this could be a red flag suggesting the coin is being manipulated.

Zaman says the Coefficient of Engagement has applications beyond the world of cryptocurrency; in fact, he recently tested it in another area notoriously difficult to predict. In a social media class, he asked his students to test whether the new method could predict movie performance. They put together historical buzz on a handful of movies, then tried to figure out which one would be successful. The animated movie Super Mario Bros. was by far the most talked about and, true to form, is now the highest-grossing film of 2023.

It gives you a way to take a subject’s overall temperature by sampling a relatively small amount of data, and it seems to predict success very well, he says. With just a few thousand tweets, you can watch a cryptocurrency, or a movie, maybe a new brand or a new product or a politician.

[ad_2]