DIY MMM ?
Of late we are getting lot of calls from prospective clients for MMM adoption. One of the curious question being “Can we DIY MMM through open source libraries?”
Our answer – Yes and No 🙂.
You can DIY MMM if:
✅ You understand the nuances of MMM (Remember MMM is not just Linear Regression).
✅ You understand the domain.
✅ You have good knowledge of statistics.
✅ You have good understanding of experimentation and causal inference.
✅ You know how the open source libraries work under the hood.
✅ You know R or Python to make changes in the open source libraries if required.
If you don’t tick all of the boxes above, I am sorry you can’t DIY the MMM.
MMM has not reached the stage of ‘simple API call’ or ‘Click once and get results’ yet.
One needs deep expertise in MMM, statistics and programming skills to know the following:
· How do we choose the best model out of the many models?
· How do we tune the models?
· How do we know if the model is correct?
· Is the saturation curve correct? What happens if we keep deploying spends beyond the saturation point?
· What should be the ideal budget allocation?
· What are the right calibrations for the MMM model?
· When is the right time to update the MMM model?
One analogy that I provide to prospective clients is that, open source MMM libraries may be like Formula 1 car. A skilled driver would be able to extract more out of the car than a layman.
You may not be able to DIY MMM but with the help of experienced hands like us you can get the maximum out of open source MMM libraries.
We have done deep dives and continue to do deep dives on many open source libraries like Robyn, Lightweight MMM and PYMC MMM etc.
Our series of posts on ‘Robyn under the hood’ is under resources. We will be publishing under the hood series on ‘Google Lightweight MMM’ and ‘PYMC MMM’. Stay tuned !!
Resources:
Robyn under the hood – https://www.linkedin.com/posts/ridhima-kumar7_marketingmixmodeling-marketingeffectiveness-activity-7001035438970847232-CWfz?utm_source=share&utm_medium=member_desktop
Image credits: Image by <a href=”https://www.freepik.com/free-photo/diy-word-tools-assortment_10890855.htm#query=diy&position=6&from_view=keyword&track=sph#position=6&query=diy“>Freepik</a>
