Many claim they can predict stock and cryptocurrency prices using machine learning; but no one can prove a profit on live data. What’s the catch?

Image for post
Image for post
Public Use Credit: pixabay.com

Note from Towards Data Science’s editors: While we allow independent authors to publish articles in accordance with our rules and guidelines, we do not endorse each author’s contribution. You should not rely on an author’s works without seeking professional advice. See our Reader Terms for details.

If you’re reading this article, you’ve likely seen blog posts/articles online using stock/cryptocurrency data and machine learning algorithms to “predict” future prices. Here, I’ve demonstrated a similar project in which I use some metrics like Tweet Volume, Google Trends Volume, Market Cap, and Trading Volume to “predict” tomorrow’s opening price. In this example, we will focus on Bitcoin prices since it is a hot topic, but this can be extrapolated to any asset as long as the data is available. Naively, one may think on a day where people are tweeting about Bitcoin, Googling Bitcoin, and trading Bitcoin more than usual, we will likely see the price of Bitcoin open higher tomorrow than it did today. Further, maybe we can actually predict tomorrows opening price with high enough accuracy based on these data to ultimately yield a profitable trading algorithm. …


Do data science competitions violate Open Source? — A case for open idea transfer and collaboration

Image for post
Image for post
freebiesupply.com

As any data scientist is probably familiar, there exists a vast world of predictive modelling competitions on the internet. Some of these competitions are incentivized financially, others just by curiosity. The basic structure for nearly all of the financially incentivized competitions is that all participants (or teams of participants) train and develop models on a training dataset and send in their submissions as predictions on a test dataset of which the labels are hidden from the competitors. Subsequently, the ‘best’ models are awarded their respective chunk of the financial reward based on some predetermined accuracy metric. Most opinions regarding these predictive modelling competitions are that competition based on financial incentive creates demand for brilliant people to discover solutions to hard problems. While I initially shared this opinion and don’t disagree that they are aiming in the right direction, I’ve come to notice inherent issues with these projects that inhibit progress in a very solvable way. After all, when an organization offers $10,000 to the best performing model in a competition, they are simply crowd sourcing for the best possible solution to their problem, right? …


Exploring the power of Reinforcement Learning through a well-known game environment

Image for post
Image for post
Credit: allthefreestock.com

Deep Q-Learning may be one of the most important algorithms in all of Reinforcement Learning as it lacks limitation on the observations it can make and the actions it can take within complex environments. This method of Reinforcement Learning incorporates deep neural networks in a way that allows an agent to ‘play’ an environment repeatedly and learn the environment over time through a system of observations, actions, and rewards. This structure has obvious benefits over a standard deep neural network implementation as it allows the agent to interact with its surroundings, receive feedback from its surroundings, and then optimize for desirable (highly rewarded) future actions. …


Is your trading strategy profitable?

Image for post
Image for post
allthestock.com

I’ve recently been very interested in cryptocurrency day trading. While a quick internet search returns a slew of various indicator ideas and trading strategies, such as EMA/SMA crossings, RSI strategies, On Balance Volume, etc., I’ve found myself never able to find a resource that allows me to answer the question: “Well, does this actually work?”. Frankly, it is impossible to know the answer to this question by looking at charts without testing the strategy over hundreds or even thousands of iterations; a tedious task for a human to pour over. I’ve seen videos and articles of others trying to backtest by hand, clicking, entering, and calculating the buys and sells dictated by their predetermined strategy. In some cases only to find the answer to their question after hours and hours of backtesting: “No, this strategy doesn’t work. On to the next one.” Other, more programmatic ways of backtesting can speed up the process, such as the TradingView pine editor, or a basic python script; but what if you want to dynamically alter things like stop loss/take profit levels, the cryptocurrencies you’re choosing to trade, or specifics of the strategy itself? Answers to these questions would entail time-consuming alterations to a simple backtesting script. Since this initial interest in cryptocurrency trading, I decided I needed a better platform that was not available anywhere on the web (that I could find free of cost) that would allow me to dynamically iterate over any alterations in any strategy that pique my curiosity. …

About

Lee Schmalz

Mathematics and Molecular Biology Graduate pursuing ideas in Data Science.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store