@black-magmar You are correct, but this kind of forward-looking is always present when you have all the data at your disposal. The important point is that there is no forward-looking in the live results, and that should not happen as the prediction will be done for a day for which data are not yet available.

@eddiee Hi, Mr. Eddie.

I am new to building strategies using ML/DL on Quantiacs and am very impressed with the OS performance of your ML strategies. I hope you can give me your contact (mail, limkedin,...) so I can learn from your experience in building an ML/DL strategy.

Sincerely thank.

@snake game said in Crypto trading:

Is there anyone that would like to share a crypto strategy on BTC that can generate a consistent flow of return at about 50-100$ a day I am beginner and would be open to any type of mentorship on this topic thanks in advance

It's great that you're eager to learn about crypto trading! Building a consistent strategy involves understanding market trends, risk management, and continuous learning. Some strategies include day trading, swing trading, or long-term investing. Start small, diversify your portfolio, and consider setting realistic goals. Don't hesitate to join online communities, follow market news, and explore educational resources.

Dear magenta.kabuto, it will be done at the open price in t+1 time.

@eddiee Dear Eddiee, yes, the rules and the universe are the same. We will need some more time to extend the universe and the data set, so we decided to run a new contest with the same rules.

Please note that according to the rules at https://quantiacs.com/contest/19

A Trading System will be deemed to be a “unique“ Trading System if it was not submitted by the same user to a previous Contest and it was not published by the Sponsor itself and it was not submitted by another user to a previous Contest or to the current Contest. The Sponsor will run on submissions a correlation filter and will have to right to disqualify submissions which are not deemed to be unique.

So re-submitting the same system will result into a system which is not eligible for a prize.

@joshua408 We allow development on our cloud or local development on user's machines. No need to open any port.

@antinomy Ty

@magenta-grimer Hi, we cannot provide the list of strategies we are still trading and the payouts. However, all the statistics are public, the new ones (since Q15) and the old ones at:
https://legacy.quantiacs.com/Systems.aspx

@theflyingdutchman Yes, we are integrating new data sources for a new asset class, once we are done (next week) the data and leaderboard updates will start again.

@nosaai Hello

Spyder should be run under conda environment

an alternative way is to clone the library from https://github.com/quantiacs/toolbox
and develop strategies inside qnt. But I recommend using the approach from the documentation.

@anthony_m Hello, we had some bug reports in this direction. Normally the issue is simply the pandas version. Could you check that your version of pandas is 1.2.5?

You can simply create a new environment:

conda create -n qntdev quantiacs-source::qnt conda-forge::ta-lib conda-forge::pandas==1.2.5 conda-forge::dash==1.18 python==3.7

@xiaolan Hello, first of all conversion xarray -> pandas -> xarray is very easy, as we answered you in the other thread you opened.

The basic reason is that xarray works really well with array with an arbitrary number of dimensions. For financial data we have normally 3 dimensions:

and xarray works really well with cross-sectional indicators ranging over several assets.

@anthony_m Yes, you are right, we are using a simplified model for slippage. In reality slippage will depend on (among other things) the traded volume. More liquid assets will be prone to less slippage.

However, for speeding up the evaluation, we are using a simplified model based on the gaps, it fits well with historical data.

Clearly slippage will be a function of the allocated USD capital to a strategy.

@xiaolan Yes, allocations are translate to orders internally, it is enough to check the variation in the allocations and transform it into number of contracts bought/sold. When we designed the toolbox the goal was to simplify development as much as possible for the users.

@support I see, need to push them to submit then....