Topics created by gjhernandezp

Dear @gjhernandezp,

That strategy is filtered out because it exceeds limits (memory or time) that a strategy has. Your strategy is using machine learning, so that is risky section and could lead to something like this. The success status is irrelevant, it is probably some edge case. The only thing that matters is the status of the strategy which is filtered.

Best regards

Thanks 🙏

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

@gjhernandezp Dear gjhernandezp,

No, models are trained from scratch taking the train_period of the data that is changing depending on the processing day. No, the retraining is done from scratch, taking the whole available data up until that point in time. That is not available at the moment, but take a note that when submitting a ML strategy it should be in a single-pass mode. For example instead of using backtest_ml function that is designed for testing purposes, one should use single-pass, for example: data_train = load_data(train_period) models = train_model(data_train) data_predict = load_data(lookback_period) weights_predict = predict(models, data_predict) print_stats(data_predict, weights_predict) qnout.write(weights_predict) # To participate in the competition, save this code in a separate cell.

@gjhernandezp Thank you for sharing your solution!

@gjhernandezp Hello, you can use them for local development. Unfortunately, we do not support yet external datafeeds after submission...it is on our to-do list.