Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

0% in mean response% from Robyn_allocator result #1186

Open
jinlin53 opened this issue Dec 10, 2024 · 1 comment
Open

0% in mean response% from Robyn_allocator result #1186

jinlin53 opened this issue Dec 10, 2024 · 1 comment
Assignees

Comments

@jinlin53
Copy link

Hi Robyn team, thanks for this amazing tool.

I tried to implement the code with the dataset you provided: dt_simulated_weekly and dt_prophet_holidays, with same hyperparameter settings and without calibration settings. As for the model, I selected one from Pareto-optimals, 5_277_3.

However, I noticed that in the allocation result, for Facebook_S, the mean response shows 0% despite the date range. You can see that in the first table, the date range is about 2 years, and in the second the date range is 4 weeks.

Screenshot 2024-12-10 at 14 34 40 Screenshot 2024-12-10 at 14 34 50

Here is the JSON file for Robyn_Model-5_277_3:
RobynModel-5_277_3.json

I'd appreciate it if there's any response on this issue.

ps.
Robyn version: 3.11.1
R version: 4.3.1

@gufengzhou gufengzhou self-assigned this Dec 20, 2024
@gufengzhou
Copy link
Contributor

This is expected. The selected model has predicted facebook_S has no effect / 0 coefficient (see grey table 1st row 3rd column), thus it'll always get 0 allocation. pick another model that has no 0 coef for any channels, you'll see "normal result".

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants