A Bayesian Approach to Media Mix Modeling by Michael Johns & Zhenyu Wang

Hi - really enjoying reading through the explanation and the commentary here. I’d love to get the sample code to explore it further.
mmcmullan23@gmail.com

Hello Michael and Zhenyu,

That’s fascinating, thank you very much for the presentation. Currently I’m developing the same approach but using DAG as a hint into how one variables distributions are affected by another. Would you mind sharing the sample code with me as well? I would love to get some extra inspiration

smmnko.a@gmail.com

Thank you!

Thank you @Michael_Johns and Zhenyu for demonstrating to us the amazing model you built at HelloFresh!

I am a Msc student in Berlin and am preparing for my thesis on MMM, specifically investigating offline media such as TV with a lot of Adstock effect and saturation effects to consider.

I would really appreciate your sample code as well. My email is winnie26wl@gmail.com

Equally, if you are interested to know the details of my thesis and results, I would love to share too in due time!

Many thanks in advance!

@Michael_Johns Thanks for the great sharing of the model you built. I am new in data science field, recently just finished an internship at a media agency. I would like to find out more about the model and would appreciated if you could send me the code as reference. My email is adamtky1314@gmail.com. Much appreciated.

@Michael_Johns - many thanks for presentation, I learnt a lot. Are you able to share the sample code with me so that I can reproduce and explore further please?
brohiamir@gmail.com

Thank you!

@Michael_Johns - Hope this thread is still active. I’m a big fan of the Bayesian approach and found it extremely practical. Wondering could you share the sample data with me to explore this method? Thank you! My email is jinzhaolulu@gmail.com.

@Michael_Johns many thanks for your informative talk. Would you share the sample code to my email - valikbug@gmail.com?

kind regards

@Michael_Johns thank you so much for this informative talk. Would you be able to share the code with me? jesuiskelly@gmail.com.
Thank you very much!
Kelly

Hi Mike and Zhenye,

Thank you for this informative talk. I am trying to implement something similar for the advertising industry.
Could you please share your example code to give it a try with Bayesian Marketing Mix Models.

My contact email: emily.starer@fastg8.com

Thanks,
Emily

Thanks for a great talk Mike and Zhenyu! Please would it be possible to share the sample code? My email’s selva86@gmail.com

Really great video and discussion on Pymc. This is a new library and technique for me and it is very fascinating. I’m currently building MMM models with regression.

Long shot here as a have a feeling this discussion has gone dark a long time ago, but I too would love to see a bit more of the code as I’m can’t quite see how we get to a prediction here. Has anyone who has left their email address actually seen a response?

In case this works, would love to see more after the “likelihood” in the video: dpthg8rkvc@privaterelay.appleid.com

Thanks Michael and Zhenyu!

Hi Mike and Zhenyu,

I’m currently trying to build up a Marketing Mix Modeling for my research and I’m really glad that I’ve found your presentation. It’s very amazing, well explained and insightful. Thanks a lot for sharing the knowledge.

I would be very grateful if you could share with me your sample code, so that I can try it out on my data.
My email address is: chaudharyveenu64@gmail.com

Thank you very much in advance.
Naina

Hello Michael and Zhenyu,
thank you for your work and the presentation, is very interesting.
I’m trying to implement a version of the work described by Jin et al. and it would be very helpful for me if you could send me your sample code, if possible I would really appreciate it !

My contact:
g.carbonara@outlook.com

Thank you a lot.
Giuseppe

Thank you very much for this video. I would love to test this approach and compare it our current approach at my company.

If you could provide any code resources for the Bayesian model and optimization that would be much appreciated.

Hi Mike and Zhenyu,

thank you for the interesting video it gives a really good overview on the MMM process you are using. I’m currently investigating in uising the same approach and it would be really helpful if you could share the code. My email address is: cnutsch@gmx.net

Thank you so much in advance!
Corinna

Hi Michael and Zhenyu,

That was really interesting approach, It would be really great if you can share the sample code (ampsin2323@gmail.com)

Best

@Michael_Johns The video is very informative and your response to people’s questions were helpful too. If you could please share the sample code with me @ jaincherry2407@gmail.com that’d be great for me try out running some models on my own for the learning purposes.

Hi @Michael_Johns, thanks for the presentation.
I want to implement a Bayesian Marketing Mix Models for learning porpuse.
Could you please share your example code ?
My contact email: jose.gmb95@gmail.com

We have also published our Bayesian MMM (numpyro), any feedback welcome

1 Like

Hi!
Thanks for the presentation, it is extremely clear.
Can I have the sample code too? I would like to experiment with it!

email: lorenzo.mezzini@gmail.com

Thanks,
Lorenzo