CustomModelWrapper.optimization_model#

CustomModelWrapper.optimization_model(num_periods)[source]#

Clone base_model and resize the channel-data variable for optimization.

Parameters:
num_periodsint

Number of optimization periods (excluding any adstock warm-up). The model will be built with num_periods + adstock_periods date steps.

Returns:
pymc.Model

A cloned model ready for use by BudgetOptimizer.