A researcher at India’s Vellore Institute of Technology claims that Deep Learning can be used to predict the price of cryptocurrencies in real-time. 

According to a blog post published on Dec. 2, data scientist Abinhav Sagar has outlined the use of a “Long Short-Term Memory (LSTM)” neural network and its ability to closely predict the price of cryptoassets. 

Sagar says that while machine learning has been used in the past to successfully predict traditional stock prices, crypto has proved to be a more difficult market, 

The reason behind this is obvious as prices of cryptocurrencies depend on a lot of factors like technological progress, internal competition, pressure on the markets to deliver, economic problems, security issues, political factor etc.

Sagar used a dataset from CryptoCompare in order to train his LSTM neural network to predict crypto prices. He evaluated the outcomes based upon Mean Absolute Error and plotted the results of his Deep Learning-produced predictions:

crypto price machine learning predictionCrypto prices predicted in real-time using machine learning | Source: TowardsDataScience

Sagar also provided the code for the project on GitHub. 

Featured Image Credit: Photo via Pixabay.com