Indian data scientists use deep learning to predict BTC prices in real time

A data scientist at the University of Technology in Vellore, India, has proposed a method that can be used to predict the price of cryptocurrencies in real time using Long Short-Term Memory (LSTM) neural networks. In a blog post published on December 2, researcher Abinhav Sagar demonstrated a four-step process on how to use machine learning techniques to predict prices in an industry that is "relatively unpredictable compared to traditional markets."
The four-step method proposed by Sagar includes: 1) collecting real-time cryptocurrency data; 2) preparing data for neural network training; 3) testing predictions using LSTM neural networks; and 4) visualizing prediction results.