Hi guys,
I was just checking out the Q17 Machine Learning Algo (With Retraining). I don't know if it's just me, but I find the following strange:

• The initial algorithm (has look ahead bias and what not) uses 54 different instruments during the backtest. As far as I can see, there is no "is liquid" filter anywhere, since this is just for educational purposes.

• When the ML algorithm is passed through the backtester, it only trades 8 instruments in the same timeframe. What gives? Is there some parameter that is tuned when using the backtester instead of the whole data? Is this an error? I'd love to keep testing and exploring ML algorithms, but I think that the total number of traded instruments over 8 years should be more than 8, right?

Please let me know what changes I can make to the code, change the data, competition type, etc. in the backtester parameters, or if this is by design.

Full data "test":

Backtester:

Hi, I'm not sure if you guys can help me out, but it's worth a shot since I really enjoy working on my strategies using the Local Development option.

I tried copying-pasting the "Q17 Supervised Learning" strategy that was uploaded to the website. I have no trouble running this strategy when just cloning it and running it from the Quantiacs Jupyter Notebooks.

However, when using the Qntdev environment I created in my computer, when I try to run the code, I get a "Wrong Data Type" Exception.

However, if I then change the competition type from competition_type='crypto_daily_long_short' to competition_type='crypto_daily_long' , it works.

What do you guys suggest I do? Maybe I should update something? I used the Conda tool to install Qntdev initially, if that helps in any way. The weird thing is that I have been able to test some long/short strategies in other personal notebooks.

I've noticed that some of my newly submitted strategies for the contest have "0 days" after submission, even though I have had them approved for some 2-3 days. I checked the leaderboard and the number of days after submission for all the submissions have not changed in a few days as well.

I went into a specific strategy and noticed I cannot choose any date after Aug 28 as the end date. Is there an issue with the updating of the leaderboard scores?

I am unsure of how many strategies we can choose to participate in the Q16 contest. On one side, when I go into the sent strategies >> candidates section, I get this message:

You have 11 strategies out of 50 candidate strategies. Strategies selected for the Crypto Daily Long contest: (11) out of 15

But the emails I get saying that the strategies are accepted read something like this:

Remember that you can have at most a pool of 50 running submissions and you should select 5 before the live evaluation phase starts.

My guess is that it is 15, since it refers specifically to the long only contest, and the email is just not updated, but I just want to make sure.

Hi guys, I think the leaderboard stopped updating again. The last date
I can check on the chart is september 28th.

Hi guys,
I was just checking out the Q17 Machine Learning Algo (With Retraining). I don't know if it's just me, but I find the following strange:

• The initial algorithm (has look ahead bias and what not) uses 54 different instruments during the backtest. As far as I can see, there is no "is liquid" filter anywhere, since this is just for educational purposes.

• When the ML algorithm is passed through the backtester, it only trades 8 instruments in the same timeframe. What gives? Is there some parameter that is tuned when using the backtester instead of the whole data? Is this an error? I'd love to keep testing and exploring ML algorithms, but I think that the total number of traded instruments over 8 years should be more than 8, right?

Please let me know what changes I can make to the code, change the data, competition type, etc. in the backtester parameters, or if this is by design.

Full data "test":

Backtester:

@support thanks, I deleted the old environment, installed it again according to the documentation, and now it is working

Hi, I'm not sure if you guys can help me out, but it's worth a shot since I really enjoy working on my strategies using the Local Development option.

I tried copying-pasting the "Q17 Supervised Learning" strategy that was uploaded to the website. I have no trouble running this strategy when just cloning it and running it from the Quantiacs Jupyter Notebooks.

However, when using the Qntdev environment I created in my computer, when I try to run the code, I get a "Wrong Data Type" Exception.

However, if I then change the competition type from competition_type='crypto_daily_long_short' to competition_type='crypto_daily_long' , it works.

What do you guys suggest I do? Maybe I should update something? I used the Conda tool to install Qntdev initially, if that helps in any way. The weird thing is that I have been able to test some long/short strategies in other personal notebooks.

@news-quantiacs That's great Thanks!

@support I'm also very eager to know what the Q17 contest brings , please keep us posted!

Hi guys, I think the leaderboard stopped updating again. The last date
I can check on the chart is september 28th.

@support Hi again guys, I think the leaderboard is not updating again

I am unsure of how many strategies we can choose to participate in the Q16 contest. On one side, when I go into the sent strategies >> candidates section, I get this message:

You have 11 strategies out of 50 candidate strategies. Strategies selected for the Crypto Daily Long contest: (11) out of 15

But the emails I get saying that the strategies are accepted read something like this:

Remember that you can have at most a pool of 50 running submissions and you should select 5 before the live evaluation phase starts.

My guess is that it is 15, since it refers specifically to the long only contest, and the email is just not updated, but I just want to make sure.

@support Thank you very much for fixing it!

I've noticed that some of my newly submitted strategies for the contest have "0 days" after submission, even though I have had them approved for some 2-3 days. I checked the leaderboard and the number of days after submission for all the submissions have not changed in a few days as well.

I went into a specific strategy and noticed I cannot choose any date after Aug 28 as the end date. Is there an issue with the updating of the leaderboard scores?