Submission failure
-
Hi there,
I submitted a strategy for crypto-futures, called Sun73_Q15_BTC_1f that was not accepted in the contest due to a Sharpe ratio lower than 1.
However, the in-sample Sharpe ratio obtained with the JupyterLab does not match the one displayed online. Both prints are shown below.
It seems that the online system almost does not trade Bitcoin after March 2017 (please see the first graph below), whereas the original system from JupyterLab trades Bitcoin on a regular basis since 2014 (as shown in last graph).
Could you please verify this mismatch?
Thanks a lot!!
-
@sun-73 ok, we will try to pinpoint the problem.
-
@support I am facing the same issue too with all my strategies I recently submitted.
-
-
@support Thank you for the prompt response. I appreciate if you could reprocess the strategy Sun73_Q15_BTC_1f after solving this cache issue. You guys are the best!
-
@support said in Submission failure:
All suspicious strategies will be reprocessed.
Do you check the strategies from all users?
Because I just have submitted one for the futures contest that stopped trading in 2007 and there are more still processing... -
Hello.
All the affected strategies returned to checking.
You can delete the strategies which you don't want to check.
Regards. -
@support Thanks! One of them got accepted now and the equity chart looks fine (4 are still being evaluated).
-
This post is deleted! -
@support Hi, the strategy Sun73_Q15_BTC_1f was accepted and the IS Sharpe looks fine. Could you please include it in the contest (since I submitted it before the deadline)? Many thanks again!
-
@sun-73
Hello.Ok. We will also allow other participants to change their selection when the checking finishes.
Regards
-
@support Great, thanks!
I was worried if the algos I submitted shortly before the deadline would actually take part in the competition (2 still are processing).An idea for the next contest:
How about 2 deadlines, one for submissions and maybe a week or two later the deadline for our final selection?
This way we could wait for the evaluations to finish and then carefully select our algorithms. It would also leave some buffer for solving technical difficulties like the one that started this thread. -
@antinomy Thanks, this is a good idea. The problem could be a bias in the results, as the out-of-sample period is already quite short (4 months), and 2 weeks which are supposed to be out-of-sample would then become in-sample.
-
@support I was rather thinking to either shorten the submission period or to start it earlier, so in this case the submission deadline would have been on May 15 for instance, the evaluation/selection period from 16th to 31st and the live period would be the same.
-
@support My last-minute-submissions have finished evaluating and are selected for the competition, can they take part now?
-
This post is deleted! -
@antinomy Yes, this we could do, it is a good idea, thanks.
-
@antinomy Could you check the submissions you see in the "Competition" section under the "In Contest" tab and let us know whether they are ok or not? Thank you!
-
@support I don't see the last-minute-submissions under "In Contest" and they aren't under "Candidates" any more. There were 4 strategies for the Futures contest called futures8, futures8a, futures9 and futures9b.
-
@support Now they're all there, thank you!
