I Tested Facebook’s Machine Learning Model in the Crypto Market

Results of using Facebook Prophet to trade cryptocurrencies

Marco Santos
Geek Culture

--

Photo by Executium on Unsplash

In the world of cryptocurrency, everyone is looking to make money. Either through mining, trading, or something else entirely. For me, I wanted to see if money could be made through trading. However, not just trading alone, but trading with machine learning!

Using machine learning to predict market prices is not a new concept. Many have done so before but I wanted to see what it was like. For me, it was not enough to just forecast prices. I wanted to see what would happen if I were to trade with those forecasted prices. That is where backtesting with machine learning comes in.

In order for me to begin this backtest on cryptocurrencies, I first needed to pick a machine learning model. Now, there are plenty of time-series machine learning models out there for experimentation, but I wanted to pick one that wasn’t so common. In the end, I chose Facebook’s own time series model — Facebook Prophet.

--

--

Marco Santos
Geek Culture

NYC Data Scientist specializing in AI/ML with a passion for code | Let’s connect! — linkedin.com/in/marco-s-santos.