The Q20 Contest Started

EDDIEE

Hi Quantiacs Team,
do I have to adjust this backtest function in order to participate in the Q20 Contest?

weights = qnbt.backtest_ml(
train=train_model,
predict=predict,
train_period=4365, # the data length for training in calendar days
retrain_interval=20365, # how often we have to retrain models (calendar days)
retrain_interval_after_submit=None, # how often retrain models after submission during evaluation (calendar days)
predict_each_day=False, # Is it necessary to call prediction for every day during backtesting?
# Set it to true if you suspect that get_features is looking forward.
competition_type='stocks_nasdaq100', # competition type
lookback_period=365, # how many calendar days are needed by the predict function to generate the output
start_date='2006-01-01', # backtest start date
build_plots=True # do you need the chart?
)

And a second question: Is the usage of fundamental data is obliged, in order to participate in the Q20 Contest or is it just a valuable option?

Best
EDDIEE

support

@EDDIEE Hi, it looks ok. Using fundamental data in strategy is not mandatory for Q20 submissions.

EDDIEE

@support Thanks, I just checked the availability of fundamental data. Unfortunately, the quality of the data before 2012 is not sufficient. Maybe you can improve this in the future.
Kind Regards,
EDDIEE

magenta.grimer

yes, I've also tried using the fundamental data but it's impossible since before a certain date its quality is not enough.....
can @support give any help about it?

support

@eddiee Thank you, yes, definitely. If you can send us some bad example (low quality), it will help, so we can focus on the most important defects found by the users.

support

@magenta-grimer Thanks, same comment as for @EDDIEE: any indication on priorities we should follow will be very appreciated

magenta.grimer

@support honestly I don't understand what you need...

I would like to use fundamental data for Q20, but its quality before 2012 seems not good enough.
I was thinking about creating an hybrid strategy that maybe uses technical indicators before 2012 and fundamental data after that, but I've struggled to create such a strategy. Maybe you could help in this regard.

Or maybe another solution could be fill the dataset before 2012 with artificially created data...

support

@magenta-grimer Can you send us a list of steps we can take to increase the quality of the data before 2012?

support

@eddiee As the problem should be (mostly) related to the fact that data are missing before 2012, one temporary solution is offered by @Vyacheslav_B here:

https://quantiacs.com/community/topic/411/error-q20-output-missing-when-submitting/10

As far as the Sharpe ratio is larger than 1 in sample, the submission will be accepted, so you will have more than 10 years of fundamental data for development stil.

support

@magenta-grimer As mentioned earlier, as the main issue is that data are missing before 2012, you can use the proposal by @Vyacheslav_B

https://quantiacs.com/community/topic/411/error-q20-output-missing-when-submitting/10

Your system will be eligible if the Sharpe ratio in sample is larger than 1, and you will have still more than 10 years of fundamental data at your disposal.

magenta.grimer

Thank you @support, maybe you can be so kind to post a complete strategy using this "trick" ? A strategy based on this fundamental dataset?

Thanks

support

@magenta-grimer hi, you can find one very simple example here:

https://quantiacs.com/documentation/en/data/fundamental.html

best regards