We apply a data-driven, user-blind approach to our selection process. We don’t look at your user background or your specific rank in the contest, but rather the performance of your algorithm within the set of construction constraints. The contest rules help guide you to create strategies that would be possible candidates for an allocation. Doing well in the contest does not guarantee an allocation, but it will improve your chances for selection. We aren’t capping on a specific number of algorithms that we’re looking for — if your algorithm passes the criteria and looks interesting, we’d love to speak with you!

We are looking for strategies that are beta-neutral, sector-neutral, and have their returns driven by the specific returns, instead of common returns. Generally, a larger universe is better to diversity away risk. As per the contest, you should use the QuantopianTradableUniverse (QTU) and optimize API for your universe selection and ordering mechanics.

We generally wait for strategies to accumulate 6 months of out-of-sample data before evaluating. This helps to corroborate the strategy’s in-sample performance.

It’s great to see your interest and I would suggest that you to focus on creating strategies that generally perform well in the contest and are consistent over time. Best of luck!

Hi Alisa
Is it accurate to assume that strategies that do not include short positions are not eligible for an allocation?
Or by beta neutral you mean strategies that are not correlated to the S&P500 (perhaps a correlation less than 40%)?
Do let me know at your convenience.
Kind regards
Savio

https://www.quantopian.com/contest/rules

Thank you Grant that is very helpful. Unless I am not understanding it there is no specific requirement to have a short position. The beta is pretty clear. Another thing not covered is if some data is imported through Fetcher. Have not fully ported over the code to the Optimize API as well. Let me see if I pass some of these hurdles eventually. Thanks very much for help. Kind regards and a pleasant evening Savio

I think you’ll struggle to create a long only market neutral strategy within the QTradableStocksUS universe.

Thank you Joakim I accept the gauntlet - will let you know how I make out.

Good luck! Going long negative market beta stocks as a ‘hedge’ perhaps? Note that ETFs that are shorting the market (SDS for example that shorts the S&P 500) are not included in the QTSUS universe.

Also, for the contest, you do need to be short as well:

Long/short: Contest entries must not have more than 10% net dollar
exposure. This means that the long and short arms of a Contest entry
can not be more than 10% different (measured as 10% of the total
capital base). For example, if the entry has 100% of its capital
invested, neither the sum value of the long investments nor the sum
value of the short investments may exceed 55% of the total capital.
This is measured at the end of each trading day. Entries may exceed
this limit and have up to a 20% net dollar exposure on up to 2% of
trading days in the backtest used to check criteria

.

Hello Joakim the way I am understanding the rules is that the 10% difference is measured on end of day holdings. Since my strategy is mainly intraday I might be able to get away with long only, you never know. In any event, it will give me satisfaction just to see the strategy being consistent - participating in the contest will be for fun and to claim bragging rights over a beer. Will be in touch - have a nice evening Savio PS I looked at short ETFs sometime back - 1x, 2x and 3x - their tracking error at the time did not make them suitable for my strategy - I understand they were synthetic shorts - I have not revisited them recently.

Fair enough Savio, and good luck! You may find that you're hitting the Turnover constraint then if you're doing mostly intraday trading, especially since you do need to close roughly half of your longs and open up short positions instead before the close. I think you'll find it difficult to meet all constraints but wish you best of luck. I'd be interested in hearing how you go.

Savio, I'll echo what's already been mentioned in this thread. Quantopian is seeking to make allocations to algorithms that have a particular risk profile, as outlined here. The contest is structured to make it easier to know if you're on the right path. Doing well in the contest is a step in the right direction.

Thank you Alisa - working on it feverishly now that Joakim has thrown down the gauntlet.

Savio -

I'd also recommend structuring your algo so that you can play around with multiple factors, and combine them. This can help smooth out returns. No time now, but if you are interested in an example, I can post one.

Thank you Grant - that is very kind of you. My current strategy is based on straight portfolio optimization although I have a pre-optimization filter. I have spent some time on flattening out the efficient frontier. I do not use Black Litterman, just plain old vanilla historical data without any of my own subjective bias. I put this together based on material I was studying for the CFA program. In theory it should work. Will let you know how I fare. Thanks very much again for your help and wish you a pleasant weekend - it is going to be a scorcher here.