- Newest
- Most votes
- Most comments
Hello,
I understand that explainability is either not created or created with all weights equal to zero. Please note that, while enabling the Holidays Featurization, it is recommended that your historical data contains at least two years of data. This allows Forecast to identify demand patters that are associated with specific holidays. After you choose a country, Holidays applies that country’s holiday calendar to every item in your dataset during training. Please refer to [1] for more details on this. If one or more attribute has an impact score of zero, then these attributes have no significant impact on forecast values. Scores can also be zero if the AutoPredictor used only a non-ML algorithm, or you did not provide related time series or item metadata. Please refer to the the best practices and restrictions from [2] when working with explainability.
Kindly try checking with the above resources. If you face any other issues or require further assistance, please reach out to AWS Support [3] along with the dataset details and job arn's, and we would be happy to assist you further. Thank you!
References:
[1] https://docs.aws.amazon.com/forecast/latest/dg/holidays.html#enabling-holidays
[3] https://console.aws.amazon.com/support/home#/case/create
Relevant content
- asked 2 months ago
- asked 4 months ago
- Accepted Answerasked 7 months ago
- AWS OFFICIALUpdated 8 months ago
- AWS OFFICIALUpdated 2 years ago
- AWS OFFICIALUpdated 3 months ago