This idea is part of the A Dollar Worth of Ideas series, with potential open source, research or data science projects or contributions for people to pursue. I would be interested in mentoring some of them. Just contact me for details.


Now that I am spending more time in on-line communities, I'm surprised by the number of people approaching the field seeking to build trading bots.

Market trading is a fascinating area with plenty of opportunities for learning topics that take a lifetime to master.

In general, I find the amount of effort behind building a trading bot to trade small amounts of capital unworthy of the expected ROI, particularly because the chances of success are slim.

The possibility of profit, though, makes people work on this really hard and to study the topics with unusual determination.

This idea refers to learning material to teach machine learning concepts, finance, risk management and decision making built on top of a trading bot being constructed. At the end of the process, the hope is for the person involved in the learning to have improved a bare bones bot in a direction of their choosing and by then to be able to make an informed decision whether to pursue the trading bot any further.