Hello everyone, I’ve been using neuralforecast and mlforecast for some time now, but I’m still kinda new to the field of time series forecasting. mlforecast greatly simplifies the process of incorporating lags and rolling window features into my models. I try to enhance my model by introducing additional features beyond the standard lags and lag transformations. Even though these exogenous variables exhibit strong correlation and have high importance scores, I’ve noticed a significant decrease in the accuracy of my model during cross-validation after their inclusion, which is very confusing to me. Here’s how I set up my model and did the cross-validation: mlf = MLForecast(models=model_1, freq='1h', lags=[1, 24, 48, 72, 168], lag_transforms={12:[RollingMean(window_size=24)], 24: [RollingMean(window_size=24)], 48: [RollingMean(window_size=48)]}, date_features=["year", "month", "dayofweek", "day", "hour"]) # Seasonal data crossvalidation_df_met = mlf.cross_validation( df=df[['ds', 'y', 'unique_id', 'is_holiday', 'is_weekday', 'temperature_2m', 'relative_humidity_2m', 'shortwave_radiation_instant', 'distance_to_holiday']], h=48, n_windows=10, ) Any ideas or suggestions would be super helpful. Thanks in advance!

Hey. You have to set

static_features=[]

to consider those features as dynamic

I am so stupid 🥲 i will review and the toturial and api doc again and give a shot tomorrow. hope it works. Much appreciated!

no worries, it's a confusing part of the library