The training models methodology for predicting the rate of cryptocurrency against the dollar two weeks ahead from the current date, so the models are rebuild on a daily basis. Model training uses the trends data from Yahoo Finance. List of cryptocurrencies: BTC, ETH, LTC, BNB, XMR, ATOM. But this list can be extended.
The training of model takes into account the news sentiment about cryptocurrency. Historical news are taken from the news sites and the actual news from the rss feeds.
Forecasting
The value of the cryptocurrency rate is predicted for the next 14 days. Data discretization - one day. Interval forecast, the range of acceptable values of the forecasted exchange rate is indicated.
Telegram bot Cryptonitto
The public part of the project is a telegram bot @cryptonitto_bot (https://t.me/cryptonitto_bot)
The bot menu is shown on the figure below.
Forecasting method
We are developing a unique forecasting method using the combination of time series prediction with news sentiment analysis.
A special service for collecting news of the cryptomarket has been developed.
The news structure is shown on the picture below.
The view of news parser is shown on the picture below.he picture
the Prophet library has been used in the pilot version of the predictive model .
Project details and contacts
The project appeared on the ML System Design Course by ODS.ai
he picture