Comments (4)
Thanks a lot @pabloduque0 it's much clearer now :)
Cheers
from lightweight_mmm.
Hello @RiccardoBarb !
- Media data can contain impressions, clicks or spend (cost). But if is indeed impressions or clicks it wont contain cost as you said.
- A single vector indicating the total cost of the channel in the data.
- When we talk about costs we refer total costs. For optimisation and other parts we refer to price as the price per unit of an impression/click.
Hope it helps! Let me know if anything needs further clarification!
from lightweight_mmm.
hi @pabloduque0 thanks for your response!
What would be the recommended variable to use for media_data? would it be better to use spend or clicks/impressions?.
Also if I decide to use spend as media_data, then wouldn't cost be redundant information? would it still be needed to fit the model?
As far as the second answer is concerned, what if I have multiple media channels? Should I insert a single vector for each channel (which, in this case, is in fact equivalent to a matrix)?
Thanks
from lightweight_mmm.
Between clicks and impressions, impressions are preferred.
In reality the costs are used for the media prior (if you are referring to mmm.fit(..., media_prior=costs)
therefore costs are still relevant as they serve as the prior. If you want to use a different prior then you mostly wont need costs. The only place where costs are "mandatory" is for ROI calculation (for obvious reasons).
Apologies if that was not clear before, what I mean is a single vector indicating the total cost each channel in the data, with ONE value per channel, so the total costs. So always one vector with one value per media channel. Eg. for three channels your costs could be jnp.array([1, 2, 3])
.
from lightweight_mmm.
Related Issues (20)
- Get contribution from predict
- How can I calibrate my predicted ROI in the MMM with my geolift result ? HOT 3
- How can I run kind of gridsearch to find the best custom priors for a hill_adstock or carryover model ?
- How can I input future media_data_test for optimization in upcoming periods? HOT 1
- How can channel-wise optimized conversions be obtained?
- Extra features
- Addressing Heteroscedasticity
- Geo level attribution and response curves
- Budget Allocation Percentage breakdown by channel HOT 10
- Question on tensorflow requirement
- Dtype object is not a valid JAX array type. Only arrays of numeric types are supported by JAX. HOT 5
- Same pre-optimization and post-optimization channel budget allocation ratios , but suggesting much higher budget instead of aligning the budget to the one i requested. HOT 10
- Paid Search bias - Nested model
- Divergences and n_eff
- Outliers and influential points
- budget allocator: How to set up lower bound and upper bound per channel?
- add got incompatible shapes for broadcasting: (95,), (90,). HOT 5
- TypeError: add got incompatible shapes for broadcasting: (58,), (54,). HOT 8
- Rendering of several plots not working! HOT 1
- Negative Values in Pre optimization predicted Target vs Post optimization predicted Target
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lightweight_mmm.