Using an LSTM for time series prediction

In this chapter, we're going to predict the minute-to-minute value of bitcoin in US dollars during the month of June 2017 by using the minute-to-minute price of bitcoin from January to May of 2017. I know this sounds really lucrative but before you buy that boat, I recommend reading through to the end of the chapter; this is something easier said and even easier modeled, than done.

Even if we were able to create the potential for an arbitrage (a difference in price between two markets due to an inefficiency) between USD and bitcoins using some model like this one, developing a trading strategy around bitcoin can be extremely complex because of the delay in finalizing bitcoin transactions. At the time of this writing, the average transaction time for a bitcoin transaction is over an hour! This "illiquidity" should be a consideration in any trading strategy.

As before, the code for this chapter is available in the book's Git repository under Chapter09. The file data/bitcoin.csv contains several years worth of bitcoin prices. We will only be using a few months of price information for our model, based on the hypothesis that the market behavior in prior years wasn't relevant to the behavior of 2017, when the cryptocurrency became popular.

Table of Contents for Using an LSTM for time series prediction

Create new playlist

Sign In

Sign Up

Table of Contents for
Using an LSTM for time series prediction