Back to Community
Update on Third-Party Corporate Pension Challenge

Hi all,

We have some exciting updates to share with you! We received 399 submissions for the Third-Party Corporate Pension Challenge and we are almost done evaluating the results!

Please check our preliminary results below:


*For this plot, we use the date range, 2014-01-04 to 2018-08-29 for in-sample, and 2018-08-20 to 2019-12-31 for out-of-sample.

Join our LIVE winner announcement and tearsheet review webinar here on Monday, April 6 at 2 PM EST.

Disclaimer

The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by Quantopian. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. No information contained herein should be regarded as a suggestion to engage in or refrain from any investment-related course of action as none of Quantopian nor any of its affiliates is undertaking to provide investment advice, act as an adviser to any plan or entity subject to the Employee Retirement Income Security Act of 1974, as amended, individual retirement account or individual retirement annuity, or give advice in a fiduciary capacity with respect to the materials presented herein. If you are an individual retirement or other investor, contact your financial advisor or other fiduciary unrelated to Quantopian about whether any given investment idea, strategy, product or service described herein may be appropriate for your circumstances. All investments involve risk, including loss of principal. Quantopian makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances.

6 responses

Thanks for the update, looking forward to the webinar next week!

I think it's important to note though that not all datasets were held out during the chosen out-of-sample (OOS) period, so it's quite possible to have trained factors on this period. For example, all price/volume data, Morningstar Fundamentals, and the two sentiment datasets, were fully available during this period.

Just my opinion, but with the new strategic pivot, I think it would make a lot more sense to have a platform-wide 2-year hold out period for ALL platform supplied datasets. That way OOS for these Challenges would be much closer to 'true' OOS. Yes, one could still get around it by sourcing datasets elsewhere and upload using self-serve, but it would be a much bigger hurdle, including having to train the factor off-platform (if done on-platform, I'm assuming Quantopian would be able to detect if one is accessing the self-serve data during the last 2 years/OOS period), and data cleaning/wrangling, etc.

Controversial maybe, but that's my opinion.

PS: Best would be to use 'live' data accumulated after the Challenge submission deadline (Kaggle-style), but that would mean having to wait 6-12 months for live data accumulate (1 or 2 months would not be enough, especially during these crazy times). Again, just my opinion.

Does the plot show all the submitted algorithms? I don't see one my old algorithms that had an in sample specific Sharpe ratio over 5. I'm curious to see how the algorithm performed since Quantopian started collecting Factset data live. There seems to be a difference in alpha decay between live captured Factset data and manually delayed data. You could see the difference in the last insiders challenge webinar, there was a group of algorithms in the IS & OOS specific Sharpe ratio stability plot that were linearly off by the same ratio. That doesn't happen by chance. It would be interesting to see if the previous challenges using only Factset data had the same bias on the IS & OSS SR Stability Plot because the cutoff between in sample and OOS for the challenges was when Quantopian started collecting FactSet data live.

Yes, one could still get around it by sourcing datasets elsewhere and upload using self-serve

Or by curve-fitting a strategy using an off-platform backtester and then implementing the same strategy on-platform. No need to use self-serve. Very simple to circumvent.

Unfortunately, this challenge appears to have degenerated into this type of 'permutations gaming'

Can't remember off the top of my head what it's called, but there's a type of "Sharpe Ratio" where the score is penalized according to how many times the strategy has been revised. Perhaps something similar would work. What about, instead of simply selecting the best strategy from each high-correlation cluster, actively dinging the scores of strategies that are in crowded clusters. That way if somebody submits 30 variations of a strategy, their best strategy will rank worse than if they had simply submitted the best one and no others. It will also select for more novel strategies in cases where many contestants submit similar strategies.

Can't remember off the top of my head what it's called, but there's a type of "Sharpe Ratio" where the score is penalized according to how many times the strategy has been revised.

Deflated Sharpe Ratio

Congrats once again to our winners!

  • Kyle M
  • Vedran Rusman
  • Oleg
  • Oleg
  • Vedran Rusman
  • Joakim Arvidsson (Cream Mongoose)
  • Indigo Monkey
  • Joakim Arvidsson (Cream Mongoose)
  • Daniele Carabini
  • Joakim Arvidsson (Cream Mongoose)
  • Bjarke Riis Larsen
  • Viridian Hawk
  • Vladimir
  • Leo M
  • Neeraj Salodia

Your prizes are being processed. You should receive an email from our payment service soon.

We wanted to give everyone a brief update on the results from the pension challenge. We gave an initial review with the team there and it went really well. They are extremely excited by the results and are looking forward to next steps. We're working with their team to ensure we construct the product that best suits their needs (i.e. risk level, exposures, turnover, etc.). Their level of engagement shows the commitment to this project and speaks to the high quality of your submissions. This is something we anticipate taking several weeks to iterate between us and hopefully we'll be able to deliver more specifics to all of you shortly!

Disclaimer

The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by Quantopian. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. No information contained herein should be regarded as a suggestion to engage in or refrain from any investment-related course of action as none of Quantopian nor any of its affiliates is undertaking to provide investment advice, act as an adviser to any plan or entity subject to the Employee Retirement Income Security Act of 1974, as amended, individual retirement account or individual retirement annuity, or give advice in a fiduciary capacity with respect to the materials presented herein. If you are an individual retirement or other investor, contact your financial advisor or other fiduciary unrelated to Quantopian about whether any given investment idea, strategy, product or service described herein may be appropriate for your circumstances. All investments involve risk, including loss of principal. Quantopian makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances.