Level: MA
Responsible Person: Yu Zhang
Keywords: Cryptocurrency, Time series, Stock 

More and more cryptocurrencies have already been traded in many centralized markets, like Binance, which are similar to stock trading. However, cryptocurrencies are different from stocks in the fact that they have no firms that can back up their price. Investors’ attitudes to them can be reflected in their price time series. In this project, we will use the machine learning method to help classify the price time series between cryptocurrencies and stocks. If the machine learning method can get higher accuracy in time series classification, it will mean that the cryptocurrencies’ prices have different patterns from the stock prices, which will also reflect that investors have different attitudes to cryptocurrency investment and stock investment.

References:

Ismail Fawaz, Hassan, et al. "Deep learning for time series classification: a review." Data mining and knowledge discovery 33.4 (2019): 917-963.