search

google / lightweight_mmm

LightweightMMM 🦇 is a lightweight Bayesian Marketing Mix Modeling (MMM) library that allows users to easily train MMMs and obtain channel attribution information.
https://lightweight-mmm.readthedocs.io/en/latest/index.html
Apache License 2.0
883 stars 188 forks source link

Low R2 value #331

Open mahaja1 opened 2 months ago

mahaja1 commented 2 months ago

I see my R2 for testing data to be 0.215. Should i still rely on the model? Also, what are the ways I can improve the accuracy of the model?

akim-collab commented 1 month ago

Hi! R^2 is recommended to look only at the training dataset. To view the quality of a model on a test dataset, you need to look at the standard quality metrics of regression models, for example, MAPE, MAE, RMSE. I also strongly recommend conducting statistical tests for the model residuals on the training dataset.