@cespadilla Hello.

The reason is in "train_model" function.

def train_model(data): asset_name_all = data.coords['asset'].values features_all = get_features(data) target_all = get_target_classes(data) models = dict() for asset_name in asset_name_all: # drop missing values: target_cur = target_all.sel(asset=asset_name).dropna('time', 'any') features_cur = features_all.sel(asset=asset_name).dropna('time', 'any') target_for_learn_df, feature_for_learn_df = xr.align(target_cur, features_cur, join='inner') if len(features_cur.time) < 10: continue model = get_model() try: model.fit(feature_for_learn_df.values, target_for_learn_df) models[asset_name] = model except: logging.exception('model training failed') return models

If there are less than 10 features for training the model, then the model is not created (if len(features_cur.time) < 10).

This condition makes sense. I would not remove it.

The second thing that can affect is the retraining interval of the model ("retrain_interval").

weights = qnbt.backtest_ml( train=train_model, predict=predict_weights, train_period=2 *365, # the data length for training in calendar days retrain_interval=10 *365, # how often we have to retrain models (calendar days) retrain_interval_after_submit=1, # 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='crypto_daily_long_short', # competition type lookback_period=365, # how many calendar days are needed by the predict function to generate the output start_date='2014-01-01', # backtest start date analyze = True, build_plots=True # do you need the chart? )

@vg2001 Hello, the Q19 is a replica of the Q18, you ccan use the same examples.

@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.

@support ok, thank you!

@pink-seel Super that you found it, please do not hesitate to ask for support!

@support Got it, thanks a lot!

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

@magenta-grimer Hello, we updated the documentation.

Now there are 78 futures contracts. Yes, we allow allocating to only 1 asset. If you trade more assets, then you can go long on some of them and short others.

Using more assets helps in increasing the Sharpe ratio, as the mean return grows linearly with the number of assets, and the volatility in the denominator with the square root of the number of assets if there are no correlation terms.

Using uncorrelated assets would then lead to a scaling of the Sharpe ratio with the square root of the number of assets. In practice, however, correlation terms are decreasing this growth.

Stated more simply, it is a good idea to avoid putting all your eggs in the same basket...

It's safe to ignore these notices but if they bother you, you can set the variables together with your API key using the defaults and the messages go away:

import os os.environ['API_KEY'] = 'YOUR-API-KEY' os.environ['DATA_BASE_URL'] = 'https://data-api.quantiacs.io/' os.environ['CACHE_RETENTION'] = '7' os.environ['CACHE_DIR'] = 'data-cache'

@rezhak21 Rules are defined at: https://quantiacs.com/contest and more details for the current contests (submission time till end of May) can be found at: https://quantiacs.com/contest/15

For Futures the in sample period starts on January 1st 2006, for the BTC Futures on January 1st, 2014

@theflyingdutchman Hello, before the end of the week the update will be ready, sorry for the delay

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

@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 Correct, allocation started one month after live phase ended. We do not release certificates, but the results are public on the page.

@support
Thanks.
You guys are the best!🏆

@buyers_are_back Hi,

Regarding your first question, yes, that is correct. As we look more into the past, it is more difficult to get data for companies which have been index members but don't exist anymore, for example. This is also related to your second question - symbols with '~1' are in almost all cases, the same companies with the same ticker symbol, but with different ISIN (International Securities Identification Number). For instance, SanDisk company ("NAS:SNDK") was standalone public company until 2016, when Western Digital acquired SanDisk. In 2025 company spinoff, SanDisk re-emerged on the Nasdaq as an independent public company, with the same ticker as it was ('SNDK'), but with different ISIN (considered as different company).
Those symbol pairs, should not have an intersection in membership ("is_liquid" field should not be 1.0 for both at the same time), otherwise it could be mistake by provider.

Hello. The processing speed has been stabilized and should now be working normally.

@anshul96go Sorry for the late answer, we missed it somehow. Yes, all submissions sent before deadline will be processed and accepted.

@nosaai Hello

Spyder should be run under conda environment

conda activate qntdev conda install spyder spyder

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.

@vyacheslav_b Apologies for the late response. Thanks for the assistance, all is now well. Cheers