Table of Contents:
- Prologue: The Sirens Beckon
- Chapter 0: The Gods’ Blessing
- Chapter 1: Moving Averages Crossover
- Chapter 2: The BumpRider
- Chapter 3 (TBD): Mean Reversion Theory as it applies to Crypto
- Chapter 4 (TBD): Momentum Based Trading, formally
- Chapter 5 (TBD): Using Recurrent Neural Networks
- Chapter 6 (TBD): Augmenting RNN’s using Sentiment Analysis and NLP
My first introduction to cryptocurrencies came in late 2013 just as the price of Bitcoin (BTC) had reached a peak of around $1,200 after starting off the year at just above $13. Forbes called 2013 “The Year of the Bitcoin” and for 16-year-old high school me, it seemed like the time to invest. Just like a sailor following the enchanting melodies of a siren, I went in head-first, not once asking myself about any potential consequences.
Then 2014 came around, the price fell down to about a quarter of its peak value and I was beginning to feel very skeptical about the prospects of cryptocurrency with each price drop. After a few bad bets on the World Cup using some BTC, I had decided to leave what little I had left until Bitcoin reached its “true potential”.
Fast forward to late 2017, the price of Bitcoin is slowly rising, activity is picking up as cryptocurrencies are now listed on many large exchanges, and it seems like a good time to use my programming skills to try and make some money off of the recent market movement. A couple of friends and I had a few ideas about some strategies to try, and for a while, we were able to develop a platform that was successful. Then, in early 2018, the Great Crypto Crash happened. Our wallets were stretched too thin, our positions halved in less than a month, and none of our strategies worked anymore. We were forced to stop when our orders started falling below the minimum tick size of some exchanges.
One thing I learned from 2014 and 2018 is that losing money sucks. More importantly, not being able to predict when you’re going to lose money sucks even more. Since then, I’ve started my course of study for a Masters Degree in Data Science at the University of Pennsylvania. It’s a degree that contains programming courses that cover Machine Learning from Data Mining to Deep Learning and statistics courses ranging from advanced Mathematical Statistics to Regression Analyses on Behavioral Studies.
My course of study has changed how I look at the world. No, I don’t believe Machine Learning is going to fix the world’s problems, at least not all of them. No, I don’t believe AI is going to bring about the end of humanity, at least probably not.
In fact, the only thing that it has definitively taught me is that there are no certainties in life. The best we can do is be able to say how likely we are to be right given what we know. Statistics provides us with the tools to do just that.
Back to Crypto. Given this new knowledge, is there any way we can leverage the power of statistics to perhaps help us avoid our previous pitfalls?
According to Ancient Greek mythology, Odysseus was the king of Ithaca who led the Greeks to victory in the Trojan War using his cunning tactics and bested sea monsters and cyclopses using his intelligence.
He similarly encountered sirens along his travels but was smarter about it.
Odysseus is also the name I have given to the automated trading platform I am working on. The goal of whatever this blog-series is will be to charge through the land of the unknown, inevitably vanquishing the beast that is Crypto, and stretch this Greek Mythology metaphor as thin as possible…