optimized spend - limit channel budget of optimal spend #127
ohad-monday
started this conversation in
Ideas
Replies: 1 comment 4 replies
-
|
Hi! I just tried replicating this using the mock data in the national-level example colab, and got a different result. Are you still seeing this issue? |
Beta Was this translation helpful? Give feedback.
4 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment

Uh oh!
There was an error while loading. Please reload this page.
-
in the demo example, let's say i want channel_0 to stay in the same level (200) of the spend for some reason.

optimization with default lower/upper limits:
I tried using the lower/upper bounds and limit channel_0 with (lower/upper limits are 0 for channel_0):
import jax.numpy as jnp
upper = jnp.asarray([0,0.9,0.9])
lower = jnp.asarray([0,0.9,0.9])
solution, kpi_without_optim, previous_media_allocation = optimize_media.find_optimal_budgets(
n_time_periods=n_time_periods,
media_mix_model=mmm,
extra_features=extra_features_scaler.transform(extra_features_test)[:n_time_periods],
budget=budget,
prices=prices,
bounds_lower_pct = lower,
bounds_upper_pct = upper,
media_scaler=media_scaler,
target_scaler=target_scaler,
seed=SEED)
optimization with custom lower/upper limits, show lower decrease in but still a decrease (150) but i want it to stay the same:

am i missing something here?
Beta Was this translation helpful? Give feedback.
All reactions