TF*IDF - "Term Frequency times Inverse Document Frequency"

I admit that when I came across this concept I was a little dubious.

In keeping with most scientific theories a concept is legitimised by addition of formula and statistics.

What I have been trying to do manually by observation of the results of the use of SEO tools such as Google Analytics and Google Search Console is to attempt to work out what words visitors use to find my pages. While this sounds like what most webmasters do when it comes to refining their pages I don't think the process has been quantified.

What Wikipedia say:

This may well be something that could be tracked in the future

At the moment I am not quite sure how.

Keyword Stuffing?