K B comments

Results 35 comments of

K B

optimize_budget with budget_bounds=None is allocating equal budget to all channels even though channels have varying RoAS levels

> [@kb-open](https://github.com/kb-open) thats a function, you can import from here: > > [pymc-marketing/pymc_marketing/mmm/utility.py](https://github.com/pymc-labs/pymc-marketing/blob/92e2a39c51c519f65bf3525761885f5f81a582fa/pymc_marketing/mmm/utility.py#L52) > > Line 52 in [92e2a39](/pymc-labs/pymc-marketing/commit/92e2a39c51c519f65bf3525761885f5f81a582fa) > > def _check_samples_dimensionality(samples: pt.TensorVariable) -> pt.TensorVariable: Thank you!

optimize_budget with budget_bounds=None is allocating equal budget to all channels even though channels have varying RoAS levels

> > [@cetagostini](https://github.com/cetagostini) It would be so great if you could kindly help here, please. > > Sure, try the following example: > > def average_response( > samples: pt.TensorVariable, budgets:...

optimize_budget with budget_bounds=None is allocating equal budget to all channels even though channels have varying RoAS levels

Thanks @cetagostini for taking time out and explaining this. I'll go through it and explore. Thank you once again.

optimize_budget with budget_bounds=None is allocating equal budget to all channels even though channels have varying RoAS levels

@cetagostini Based on this [YouTube video](https://www.youtube.com/watch?v=lJ_qq_IVUgg) where Thomas Wiecki was present, which was posted just 1 year back, there were alternate methods to do budget optimization. Please refer to video...

optimize_budget with budget_bounds=None is allocating equal budget to all channels even though channels have varying RoAS levels

> [@kb-open](https://github.com/kb-open) Thanks for bring questions and challenges, I'll probably try to take a look to your example in the following weeks, and train a model as the one described...