Data Science Without Makeup by Zhilkin Mikhail;

Author:Zhilkin, Mikhail;
Language: eng
Format: epub
Publisher: CRC Press LLC
Published: 2021-08-28T00:00:00+00:00

how to QA all this?

When thinking about QA, it makes sense to start at the right end of the diagram:

Communication

This is arguably the most important and at the same time the vaguest area of the process. “Data translator” may be the next sexiest job of the 21st century.4 At the moment, however, most companies have to make do with the same data scientist who has made the thing to be communicated.

The most important factor in communication of data science results is consistency. The less is left open to interpretation, the less risk of misinterpretation.

Consistency is a spectrum, and we can look at a few distinct levels:

No structure at all: Every data scientist reports results as they see fit. This is obviously not ideal and leaves a lot of room for interpretation and personal biases.

Shared vocabulary: Data scientists and everyone else have the same idea of what, for example, “DAU” or “conversion rate” are. This is the bare minimum required for effectively communicating data science results. Many organizations can be found at this level.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.