@support ok, I see, all my systems look processed btw

@anthony_m Hi, sorry and thanks for the note, it is a bug we have fixed recently. If you try to submit your system now (a copy of the Q16 template) you will get an error message telling that the system is not eligible for a prize because it correlates too much with a template.

@nikos84 Hi, no, you should not provide your own data for defining the top10 cryptocurrencies according to market capitalization. Each asset for this contest has a field called "is_liquid" which gets values 0 (not in the top 10 according to market capitalization) or 1 (in the top 10 according to market capitalization). You can read it using:

is_liquid = data.sel(field="is_liquid")

When you define allocation weights later you can simply apply the filter as follows:

weights = weights * is_liquid

where "weights" are the allocation weights. The filter will set to zero weights for assets which do not belong to the top 10 according to market capitalization at a specific point in time.

@anthony_m Sorry, the problem is that we did not update the precheck file to reflect the "cryptodaily" contest, we will fix the issue....Note that "precheck" was a code used at the beginning for checking the output. Later we implemented a multi-pass backtester which makes automatically the checks. The call in the quick start:

weights = qnbt.backtest( competition_type= "crypto_daily_long", load_data= load_data, lookback_period= 365*4, start_date= "2014-01-01", strategy= strategy, analyze= True, build_plots= True )

makes the needed checks, and you can read output info in the notebook.

@antinomy Hello, sorry for the delay in the answer, the problem has been fixed in the meanwhile. If correlations are too high, you will get a warning. Note that correlations will be checked against template code and submissions to past contests of the same kind (which are not present currently as this is the 1st crypto long-only contest we run).

@wool-dewgong Hello, yes, if you work online you have a personal area at your disposal where you can save and load files. It is the same area where your strategy.ipynb file resides.

As far as tensorflow and pytorch are concerned, you can install them in your environment using the init file you find in your area (after cloning a strategy, or creating a new one) using conda or pip.

@support yes, they have

@support The webpage is fine now. Thank you for the prompt response!

@antinomy great! Sorry, there were many submissions on the last day.

We managed to reproduce this issue and we fixed it.

@captain-nidoran hi, all your strategies which will take part to the contest should be under the "In Contest" tab in the "Competition" section.

The migration "Candidates" -> "In Contest" was not immediate as we released minor improvements to the front-end side once the submission phase was over.

@magenta-grimer thank you @support 🙇 🙇 🙇 🙇 🙇 🙇
My compliments four your exceptional python skills

@sheikh Thanks, could you post the log you see on the notebook when the code fails? Thank you!

@support Thanks, mailing you!

@support Great! This route opens new possibilities in terms of model design. Thanks a lot!

@magenta-grimer sorry now it seems to work as it is....

Thank you for the report. The template has been updated.

@support Thank you once again. You guys are the best!

@magenta-grimer There are 2 things you might want to change:

1: the lookback_period is 365 but you want a 400-day SMA. This will only produce NaNs, so the boolean array sma20 < sma20_crypto will be False everywhere resulting in -1 weights. 2*365 as lookback does the trick for these settings.

2: Bitcoin is trading 24/7, futures aren't. Better use crypto.time.values instead of futures.time.values for the output of load_data.

There might be something else that I didn't catch but the resulting sharpe is at least close to what would be expected (1.109 with 5 and 385)

@support I have done that twice before my post, but now F_RY looks fine. There are several directories with scripts and notebooks I use with qnt, so maybe I deleted the wrong data-cache before...
Thanks for fixing the data!