Machine learning distributions
The machine learning model can be leveraged to distribute daily forecast volumes across
each interval. The model generates distributions by analyzing the past 8 weeks of historical
data. Distributions are generated during training for each driver that is configured to use
machine learning forecasting. The data analysis provides a ratio for each interval on each day
of the week that is used to distribute daily forecast volumes.
To use machine learning distributions, distributions must be created for each driver. These distributions must use the distribution method Automatically generate distribution. The driver configuration must also be updated to use the new distribution.
See these topics for more details: