ML Pipeline for Spot-Checking Multiple Models

Implementing data science projects is predominantly an iterative process. One critical decision point in the data science life cycle is determining what model to try in what scenario. This decision of what model to use in what scenario is arrived at after different experiments with multiple models. This process is called spot-checking models.

Spot-checking models is quite a laborious process. We have to experiment with multiple models and different permutations of model parameters until we can find the best model. The final selection of the model is based on its performance on the test set. All these processes are quite time-consuming when implemented individually.

ML pipelines can be used to make this process easy to implement. We will see this process in action in the next exercise, where we will do the spot-checking of four different models.

Exercise 16.05: Spot-Checking Models Using ML Pipelines

In the previous exercises...