Updates to machine learning code and tweets

by Dan McKeown

Nov 19, 2018

Since the pacificpelican2 account started publishing predictive ML Scores for Bitcoin (BTC) price based on historic data, the code has been tweaked a few times to make the algorithm both more responsive to recent movements and aware of a larger data set.

When pacificpelican2 started last month it included an ML Score where a value less than 0.5 anticipates a price decline while greater than 0.5 expects an increase in the Bitcoin price. (Of course these are just automated predictions and can be innaccurate.) But now, the tweets also include information about the recent (more or less current) Bitcoin price, the previous Bitcoin price recorded (typically from an hour ago), and information about how the ML Score and Bitcoin price have changed (Δ) since the last time they were recorded, as you can see below: