MultiDimensionalBudgetOptimizerWrapper.sample_response_distribution

MultiDimensionalBudgetOptimizerWrapper.sample_response_distribution(allocation_strategy, noise_level=0.001, additional_var_names=None, include_last_observations=False, include_carryover=True, budget_distribution_over_period=None)

Generate synthetic dataset and sample posterior predictive based on allocation.

Parameters:

allocation_strategyDataArray

The allocation strategy for the channels.

noise_levelfloat

The relative level of noise to add to the data allocation.

additional_var_nameslist[str] | None

Additional variable names to include in the posterior predictive sampling.

include_last_observationsbool

Whether to include the last observations for continuity.

include_carryoverbool

Whether to include carryover effects.

budget_distribution_over_periodxr.DataArray | None

Distribution factors for budget allocation over time. Should have dims (“date”, *budget_dims) where date dimension has length num_periods. Values along date dimension should sum to 1 for each combination of other dimensions. If provided, multiplies the noise values by this distribution.

Returns:

az.InferenceData

The posterior predictive samples based on the synthetic dataset.