Can you make predictions on bitcoin using machine learning?

Bitcoin is a decentralised, open-source, peer-to-peer network that operates without a central authority or banks. Although I personally do not own any bitcoins, it is a very popular currency and lots of people do. For instance, whilst researching this piece, I noted that 1 bitcoin is £49,906.22! With a rate like that, I don’t think I’m going to be purchasing any bitcoins anytime soon.

Because there is so much interest in bitcoin, I thought it would be a good idea to analyse this currency. One question that I posed is if one can use machine learning to make predictions on bitcoin.

I have written the program that I used in Python, using Google Colab, which is a free, online Jupyter Notebook.

After I created the Jupyter Notebook, I imported the libraries that I would use to execute the program, being:-

1. Pandas to create dataframes and manipulate data,
2. Numpy to create numpy arrays and make mathematical computations,
3. Datetime to timestamp dates,
4. Sklearn to provide machine learning functionality,
5. Matplotlib to visualise the data, and
6. Seaborn to statistically visualise the data.