Sentiment Analysis Proves Profitable for Trading Bitcoin (BTC)


Leveraging sentiment data for investment signals is not a new practice, especially among professional traders, but little evidence is currently available as to its efficacy within the crypto market.

One investor recently set out to prove that a sentiment-driven approach can be profitable when trading Bitcoin (BTC). In a recent post on Hacker Noon, Marc Howard showed that using daily exchange price data and Google Trends keyword sentiment yielded a 29% over 90 days for a $28,839 profit.

With his approach, Howard researched the Google trend data for “BTC USD” and “Buy Bitcoin” over a 90-day period and found a notable pattern.

“‘BTC USD’ to ‘Buy Bitcoin’ ratio is less than ~3:1 (specifically <35%) at the BTC price “close” for the day, the following day‚Äôs close price¬†increases. If more than a ~3:1 ratio (specifically >35%) (i.e. 4:1 or 5:1) then its a signal to sell because the subsequent day’s price¬†decreases,” said Howard.

Using the pattern, Howard added a second layer to make the signal more sensitive. He sorted each daily outcome by the price change for that day, taking only positive ratios that occurred on the same day that Bitcoin traded $80 above the prior day’s close price.

Howard has managed to turn¬†his original $100,000 investment into¬†$128,839¬†using the model. However, he notes that it is far from perfect and that he has yet to test outcomes outside of the $6,000-$8,000 price range. He is even recruiting¬†data scientists interested in working with him on the model — more information can be found here.

More: How I Created a Bitcoin Trading Algorithm Using Sentiment Analysis With a 29% Return

Disclaimer: This article’s author has cryptocurrency holdings that can be tracked here. This article is for informational purposes only and should not be taken as investment advice. Always conduct your own due diligence before making investments.

Leave a Reply

Your email address will not be published. Required fields are marked *

Related Posts