Using AutoML solutions

Writing code from scratch to perform ML requires specific knowledge that a general analyst using Power BI often doesn’t have. That’s why we recommend using AutoML processes from here on out for analysts who don’t have a data science background. Does this mean that anyone can build an accurate ML model without knowing the theory behind the science, just by using AutoML algorithms? Absolutely not! It’s important to keep the following in mind:

IMPORTANT NOTE

An AutoML tool relieves the analyst of all the repetitive tasks typical of a ML process (hyperparameter tuning, model selection, etc.). Often, the tasks that require specific theoretical knowledge on the part of the analyst (e.g., missing value imputation, dataset balancing strategies, feature selection, and feature engineering) are left out of the automated steps. As a result, if the appropriate transformations known only to an expert are not applied to the dataset...