I wrote a research notebook on an idea I had for a trading signal. This is an example of how to use the research platform for a semi-thorough investigation of a potential strategy.
Summing up the investigation in short:
Thesis: some companies make much more money per employee than others. This suggests that these companies are run more efficiently and are more adept at creating value. These companies should therefore outperform their competitors, which should be reflected in the stock price.
Conclusion: how much money a company makes per employee is not a viable trading signal. It appears to be unrelated to the change in stock price over a 1-year period. Attempting to trade on this signal generally gives very poor results.
Note: there currently is a bug: when you attempt to "View Notebook," the LaTeX will not render. This bug is in the process of being fixed, but if you wish to view rendered LaTeX, you will need to clone the notebook. You should not need to run any of the sections of the notebook. If you do need to run some notebook sections for whatever reason, please note that you will not be able to run some of the backtest-related code sections, because they draw on my backtests, which are private to my profile and are impossible for me to make available.
