Last week we announced that we'd be using updated rules for the June contest. You can see them implemented now on the leaderboard. You can see how algos with a beta between 0.3 and -0.3 are ranked above algos that don’t make the beta cutoff.
A refresher on the beta cutoff calculation: We are computing your beta to SPY over a trailing 1-year period at the end of each month for a year, and then averaging those results. In actual practice, that means computing your beta to SPY for the year ending April 30, 2015, for the year ending March 31, 2015, for the year ending February 28, 2015, etc. until we have 12 computations, and then averaging them.
We don't yet have an automated way of showing you that cutoff number in the backtest, but we do have a way for you to calculate it yourself:
- Run a full minute-mode backtest from 5/1/2013 to 4/30/2015.
- Click into the ‘beta’ tab on the left side of your full backtest screen.
- Take the mean of the twelve most recent values for twelve month rolling beta (the rightmost column)
This value will match what you see on the leaderboard.
As the contest kicks off future months, we're going to recompute the filter to use the latest 12-month period. This means that with every new contest, everyone will get a new beta score.