Building Causal Expertise is a Process, Not an Event
Causal modeling is an umbrella term for a wide range of methods that allow us to model the effects of our actions on the world.
Causal models differ from traditional machine learning models in a number of ways.
The most important distinction between them stems from the fact that the information contained in observational data used to train traditional machine learning machinery is — in general — insufficient to consistently model the effects of our actions.
The result?
Using traditional machine learning methods to model the outcomes of our actions leads to biased decisions most of the time.
A good example here is using a regression model trained on historical data to determine your marketing mix.
Another one?
Using XGBoost trained on historical observations to predict the probability of churn and sending a campaign if the predicted probability of churn is greater than some threshold.