@iron-tentacruel Sorry for the delay in the answer. We recommend conda as we can better track dependencies. With conda you can create locally an environment which mirrors the one on the Quantiacs server and you can work locally as you would on the server. If you need a specific version of a package, please let us know.

@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.

@blackpearl Hello. I don’t use machine learning in trading, and I don’t have similar examples. If you know Python and know how to develop such systems, or if you use ChatGPT (or similar tools) for development, you should not have difficulties modifying existing examples. You will need to change the model training and prediction functions.

One of the competitive advantages of the Quantiacs platform is the ability to test machine learning models from a financial performance perspective.

I haven’t encountered similar tools. Typically, models are evaluated using metrics like F1 score and cross-validation (for example, in the classification task of predicting whether the price will rise tomorrow).

However, there are several problems:

It is unclear how much profit this model can generate. In real trading, there will be commissions, slippage, data errors, and the F1 score doesn’t account for these factors. It is possible to inadvertently look into the future. For instance, data preprocessing techniques like standardization can leak future information into the past. If you subtract the mean or maximum value from each point in the time series, the maximum value reached in 2021 would be known in 2015, which is unacceptable.

The Quantiacs platform provides a tool for evaluating models from a financial performance perspective.

However, practice shows that finding a good machine learning model requires significant computational resources and time for training and testing. My results when testing strategies on real data have not been very good.

@commanderangle Dear commanderangle,

If you use ML in your strategy but not select that option we can't guarantee for how your strategy will be evaluated and it could be filtered out.

Regards

@multi_byte-wildebeest Hi. Without an example, it's unclear what the problem might be.

If you use a state and a function that returns the prediction for one day, you will not get correct results with precheck.

This was discussed here: https://quantiacs.com/community/topic/555/access-previous-weights/18

@gjhernandezp Hi,
sorry for delay, you can check this topic:
https://quantiacs.com/community/topic/564/collections-has-no-attribute-iterable

@vg2001 Hi, the limit refers to point-in-time evaluation, namely 10 minutes per point in time, where points in time are the processed historical days.

@vg2001 Sorry for the delay. It is a bit different, we reserve the possibility to scale down volatility to 5%. This can happen if the algorithm (for example) concentrates allocations in a few assets and becomes inherently very risky to be traded.

@illustrious-felice Hi, sorry for the delay, we extended the deadline.

As far as looking forward is going on, this does not take place during the real-time simulation, as the code cannot access by construction the new data. This is true even if the code is written in a single-pass way.

If the user uses a single-pass implementation, however, looking forward in the in-sample period is possible of course, there it is responsibility of the user to prevent it. Single-pass has access to all the time series.

@magenta-kabuto Hi, did you try it? The slice function is designed to return all weights.

@multi_byte-wildebeest Hi, these limitations refer to the processing time per point in time, not for the full strategy.

If it takes 10 minutes per historical day, and the simulation has to take into account 250 days for let us say 10 years, the multi-pass simulation would process 6 days per hour, 144 days per real day, that means 2 weeks of processing time for the full submission, it is a lot of time.

@support

Thank you, I noticed some changes on the rules so I have to reimplement the strategy anyway.

@newbiequant9696 Hello. Everything works correctly in the online environment. Where do you run your code? Try recloning your strategy.

import qnt.data as qndata import qnt.stats as qns import qnt.graph as qngraph data = qndata.stocks.load_ndx_data(min_date="2005-01-01", assets=['NAS:GOOGL'])

12689361-ffcc-4ea5-b1b6-1c1704399adc-image.png

Dear @quani42,

Your submissions are in the queue and will be processed. Also, all submissions that are sent to the contest before the deadline will be eligible to take part in it.

Regards

@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.

@support
Actually, I've write the weights to the output function.
螢幕擷取畫面 2024-04-24 235034.png
I think the reason might be that the data was out-of-date when the strategy received at the weekend. After the data update in the next day, it failed to pass the test.

@newbiequant96 no problem.
I think the issue now is unrelated to the the previous issue. If you can show what is written above return code 1, I can maybe help.
It seems to be an issue in the code.
Regards

Dear @lookman,

Thank you for pointing at a problem with fundamental strategies. We are working on implementing a fix as soon as possible.

Regards

@buyers_are_back Hi,
the update was related to market_capitalization field availability and correctness, as vyacheslav_b described. Unfortunately, at the moment we cannot provide missing fundamental data, like number of ordinary shares, for some stocks (e.g. META). We are going to investigate potential new data sources in order to improve our datasets.
Regards,

@stefanm said in Collections has no attribute Iterable:

pip install progressbar2==3.55.0

Thank you so much @stefanm for support. Yes, it did work. Although on installation I did get these complaints:
qnt 0.0.306 requires tabulate>=0.9.0, but you have tabulate 0.8.10 which is incompatible.
qnt 0.0.306 requires xarray==0.20.2, but you have xarray 0.20.1 which is incompatible.

Also, my apologies for the late response. I had to put things aside for a day or so. Once again, thank you.