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

MMM Case Study from PyData Global #1044

Merged
merged 25 commits into from
Oct 17, 2024
Merged

MMM Case Study from PyData Global #1044

merged 25 commits into from
Oct 17, 2024

Conversation

juanitorduz
Copy link
Collaborator

@juanitorduz juanitorduz commented Sep 17, 2024

Closes #1014


📚 Documentation preview 📚: https://pymc-marketing--1044.org.readthedocs.build/en/1044/

@juanitorduz juanitorduz self-assigned this Sep 17, 2024
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

@juanitorduz juanitorduz added the docs Improvements or additions to documentation label Sep 17, 2024
@juanitorduz juanitorduz marked this pull request as draft September 17, 2024 10:49
@juanitorduz juanitorduz added this to the 0.10.0 milestone Sep 17, 2024
@wd60622 wd60622 added the MMM label Sep 28, 2024
Copy link

codecov bot commented Sep 30, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 95.56%. Comparing base (429b955) to head (34ffcff).
Report is 1 commits behind head on main.

Additional details and impacted files
@@           Coverage Diff           @@
##             main    #1044   +/-   ##
=======================================
  Coverage   95.56%   95.56%           
=======================================
  Files          39       39           
  Lines        4013     4015    +2     
=======================================
+ Hits         3835     3837    +2     
  Misses        178      178           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

pymc_marketing/mmm/mmm.py Outdated Show resolved Hide resolved
Copy link

review-notebook-app bot commented Oct 7, 2024

View / edit / reply to this conversation on ReviewNB

cetagostini commented on 2024-10-07T14:30:21Z
----------------------------------------------------------------

Nice! I would add a note just to mention that, although good as a business practice or for stakeholder management, you must be careful when adding these constraints because basically, by decreasing flexibility, you risk to not finding the most optimal solution.

For example, the true global minimum in our function might be outside these constraints, especially in cases where we add too many of them.


Copy link

review-notebook-app bot commented Oct 7, 2024

View / edit / reply to this conversation on ReviewNB

cetagostini commented on 2024-10-07T14:30:22Z
----------------------------------------------------------------

Could we mention how uncertainty increases given the new level of spending? Historically spending around display, for example, was 200K to 250K and we are recommending 350K or so. This is reflected in the posterior uncertainty when estimating the OOS.

ps: We can preface this by mentioning that this risk/best option dynamic will be something that will soon be added to the optimizer.


juanitorduz commented on 2024-10-17T19:15:59Z
----------------------------------------------------------------

great point! added!

Copy link

review-notebook-app bot commented Oct 7, 2024

View / edit / reply to this conversation on ReviewNB

cetagostini commented on 2024-10-07T14:30:23Z
----------------------------------------------------------------

I think it would be interesting to make a comparison with total sales with and without optimization, with their respective intervals. What do you think? It should be relatively simple.


@juanitorduz juanitorduz force-pushed the mmm_casestudy branch 3 times, most recently from fe7e249 to 41adc53 Compare October 15, 2024 17:49
Copy link

review-notebook-app bot commented Oct 16, 2024

View / edit / reply to this conversation on ReviewNB

wd60622 commented on 2024-10-16T20:51:11Z
----------------------------------------------------------------

"guide you through"

trough -> through


Copy link

review-notebook-app bot commented Oct 16, 2024

View / edit / reply to this conversation on ReviewNB

wd60622 commented on 2024-10-16T20:51:11Z
----------------------------------------------------------------

only mmm? 😄


juanitorduz commented on 2024-10-17T19:09:25Z
----------------------------------------------------------------

short and sweet ;)

Copy link

review-notebook-app bot commented Oct 16, 2024

View / edit / reply to this conversation on ReviewNB

wd60622 commented on 2024-10-16T20:51:12Z
----------------------------------------------------------------

I know dims="channel" is done automatically in the MMM class. Does having those dims explicitly here help solidify that the custom prior for saturation is one per channel?

Thoughts?


juanitorduz commented on 2024-10-17T19:13:24Z
----------------------------------------------------------------

yes! I like the idea

Copy link

review-notebook-app bot commented Oct 16, 2024

View / edit / reply to this conversation on ReviewNB

wd60622 commented on 2024-10-16T20:51:13Z
----------------------------------------------------------------

I'm confused by the "11.8% <0 < 88.2%"


juanitorduz commented on 2024-10-17T19:18:17Z
----------------------------------------------------------------

This is to compare about the zero value. I will clarify.

Copy link

review-notebook-app bot commented Oct 16, 2024

View / edit / reply to this conversation on ReviewNB

wd60622 commented on 2024-10-16T20:51:14Z
----------------------------------------------------------------

mos -> most


Copy link
Contributor

@wd60622 wd60622 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just the comment about the 80% then looks good! 🚀

@juanitorduz
Copy link
Collaborator Author

Thank you very much for all the feedback! 🚀

@juanitorduz juanitorduz merged commit 6811395 into main Oct 17, 2024
12 checks passed
@juanitorduz juanitorduz deleted the mmm_casestudy branch October 17, 2024 21:14
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
docs Improvements or additions to documentation MMM
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Port MMM Example from PyData Global
2 participants