We have chosen the worst possible month to start forecasting cryptocurrencies prices, namely the Bitcoin forecast. This largest and perhaps most important currency in the world of crypto has never been particularly stable. The events around the COVID-19, on the other hand, only increased the exchange rate fluctuations. The drop from over 9,000 USD to just over 4,000 USD in such a short period was unprecedented. Even in this world.
But who could have foreseen it. And besides, we once had to start 🙂
How we predict the changes in exchange rates, we described in the article “Sentiment or emotions on the crypto stock market?“. We decided on our Facebook group to publish the forecast course every day. In this way we wanted to show ourselves and the world (such as our Urbi et Orbi) the effectiveness of our predictions. That’s why we created a Sentistock group on Sentimenti’s Facebook profile in early March. At the same time, we had the last internal arrangements concerning the scope and form of publication. That’s why the first premiere entry appeared on March 16th and with some technical interruptions continues until now.
The standard daily signal contains the following data:
- fixed average price measured from 24 closing prices, calculated each time for a full hour, fixed at 16:00 on the day of publication;
- average daily rate of exchange, calculated until 16:00 the following day;
- number of mentions taken into account.
In the comments we publish information about the accuracy of our prediction.
Well, that’s probably what interests you most. So:
How did our effectiveness work out – the Bitcoin forecast
For the whole of March 2020 the effectiveness of the trend change prediction was 77.42%. For the shorter period, published on the facebook group, i.e. since 16 March, the effectiveness was 75%.
What data do we analyse before we make a prediction?
In conclusion, throughout March, we collected 77 923 mentions, from such sources as: Facebook, Twitter, internet forums, websites, blogs. The daily average analyzed by us is about 2 500 mentions. Additionally the individual medium that stands out is Twitter.
Finally, the data collected constitute the material that is analyzed by Sentitool. In other words, by the most important part of our prediction model, the so-called regresor (analyzer of 8 emotions, positive and negative sentiment and arousal). Those more interested are referred to a few articles on our blog.
Probably April will turn out to be more demanding. Moreover, the situation around COVID-19 spreading around the world will be felt also in cryptovalut courses. Above all, we will certainly inform you about it in the next article! 🙂