Finding the optimal model with Automated Machine Learning
Automated Machine Learning is an exciting new trend that many (if not all) cloud providers follow. The aim is to provide a service to users that automatically preprocesses your data, selects an ML model, and trains and optimizes the model to fit your training data to optimize a specified error metric. This will create and train a fully automated end-to-end ML pipeline that only needs your labeled training data and target metric as input. Here is a list of steps that Automated Machine Learning optimizes for you:
- Data preprocessing
- Feature engineering
- Model selection
- Hyperparameter tuning
- Model ensembling
While most experienced ML engineers or data scientists would be very cautious about the effectiveness of such an automated approach, it still has a ton of benefits, which will be explained in this section. If you like the idea of hyperparameter tuning, then you will find value in Automated Machine...