What Drives Cryptocurrency Prices?
Nico Smuts · ACM SIGMETRICS Performance Evaluation Review · 2019
The Google Trends 1 search analysis service and the Telegram 2 messaging platform are investigated to determine their respective relationships to cryptocurrency price behaviour. It is shown that, in contrast to earlier findings, the relationship between cryptocurrency price movements and internet search volumes obtained from Google Trends is no longer consistently positive, with strong negative correlations detected for Bitcoin and Ethereum during June 2018. Sentiment extracted from cryptocurrency investment groups on Telegram is found to be positively correlated to Bitcoin and Ethereum price movements, particularly during periods of elevated volatility. The number of messages posted on a Bitcoin-themed Telegram group is found to be an indicator of Bitcoin price action in the subsequent week. A long shortterm memory (LSTM) recurrent neural network is developed to predict the direction of cryptocurrency prices using data obtained from Google Trends and Telegram. It is shown that Telegram data is a better predictor of the direction of the Bitcoin market than Google Trends. The converse is true for Ethereum. The LSTM model produces the most accurate results when predicting price movements over a one-week period.