https://github.com/nixtla logo
#neural-forecast
Title
# neural-forecast
m

marah othman

07/19/2023, 11:09 AM
To generate the forecast, we’ll use the MSTL model, which is well-suited for low-frequency data like the one used here. We first need to import it from
statsforecast.models
and then we need to instantiate it. Since we’re using hourly data, we have two seasonal periods: one every 24 hours in the documentation from anomaly detection why you here conside the hourly frequency as low frequency ?
could you see here also please , what you recommend after getting the anomaly points do you advice to remove them from the data ?? and replace it by what or something else? @Cristian (Nixtla)
c

Cristian (Nixtla)

07/20/2023, 4:07 PM
Sorry, I didnt understand the initial question
m

marah othman

07/20/2023, 8:00 PM
It seems there might be a misunderstanding or potential mistake in the documentation regarding the terminology. Typically, "low frequency" data refers to data that is sampled or recorded at a lower rate, such as daily, weekly, or monthly intervals. Conversely, "high frequency" data refers to data that is recorded at a higher rate, such as hourly, minute-by-minute, or second-by-second intervals.,correct it me if i am wrong please .
@Cristian (Nixtla)