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:

Crypto prices in collapse

by Dan McKeown

Nov 19, 2018

fowlFiveIndex-11-19-2018
The Fowl Five Index of cryptos has seen a large decline in the last few days after a period of relative stability as Bitcoin, Ethereum, Litecoin and many other cryptocurrencies fell in concert while US equity markets continue to fall as well.
Bitcoin was at lows for 2018.

Machine learning from historic BTC data

by Dan McKeown

Oct 23, 2018

I designed a machine learning algorithm that analyzes a series of hourly Bitcoin prices and then creates a "score" for predicting the next hour somewhere between 0 and 1 (the higher the score, the more likely that the price will be higher in one hour).

A version of this tool is available on the web; however (as that site notes) it is stuck training on older data.

On my computer, I have new data continuously being pulled in from the web (every hour, when the system is running anyway). So it is able to create a new score every hour. Now I have created a Twitter account that posts the hourly score.

This is an example of one of the tweets on this account:
Screenshot-pacificpelican2

Now predicting the future is an uncertain task ("always in motion is the future") and these predictions may be inaccurate. This is research data right now and I would be hesitant to use it for production purposes.

Crypto market shows slight uptick

by Dan McKeown

Jul 31, 2018

fowlFiveChart2018-07-31

The Fowl Five Index of Cryptos moved up a little for the month of July as Bitcoin and other major cryptos recovered slightly from the lows of June. Uncertainty still lingers in the market as the last few days have seen most cryptos giving back a bit of the recent gains.

A big crypto rally leads to profit-taking

by Dan McKeown

Apr 25, 2018

fowlFiveChartApril12-25-2018-
A spike in the cryptocurrency markets over the last couple weeks has run into what appears to be a round of profit-taking over the last day as some investors appear ready to cash out after a run-up that saw Bitcoin go from below $8000 to over $9000 before settling back down around $8750 as of this writing. The Fowl Five Index of cryptocurrencies moved from down below 1000 to up over 1200 before receding to around 1175 right now, its big move helped by the recent surge in price of Bitcoin Cash.