Member-only story
In my last blog post, I asked the question if it is possible to predict bitcoin prices using machine learning. I used a technique that I had found a while earlier, and that blog post can be read here:- https://medium.com/@tracyrenee61/can-you-make-predictions-on-bitcoin-using-machine-learning-f410fb729014
In this blog post I have reframed the question and ask if it is possible to predict bitcoin prices using a recurrent neural network (RNN). A RNN is one of two broad types characterised by direction of flow of information between layers. It is a bidirectional artificial neural network (ANN), meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as handwriting recognition or speech recognition. In this instance, however, a RNN is going to be used to predict on time series data, being bitcoin.
In order to answer this question, I have written a program in Python using Google Colab, which is a free online Jupyter Notebook hosted by Google.
