When your ML model is 'enough good'? When a Mean Absolute Error is 'enough good'? Is this the only metric we can use to evaluate a ML model?
In this repository I've analized the 'diabetes dataset', comparing different models to understand how a ML model can be considered 'enough good', based on the metrics.
It came out a little long work and I decided to write an article, divided in two parts, to better explaining the analysis I made in this repo.
You can find the first part here
The second part is here