A/B Testing and Experimentation for Beginners

This course is all about A/B testing.

A/B testing is used in all places. Marketing, retail, newsfeeds, internet marketing, and extra.

A/B testing is all about evaluating issues.

If you’re a knowledge scientist, and also you need to inform the remainder of the corporate, “Logo A is better than logo B”, effectively you’ll be able to simply say that without proving it utilizing numbers and statistics.

Traditional A/B testing has been around for a very long time, and it’s stuffed with approximations and complicated definitions.

In this course, whereas we are going to do conventional A/B testing to admire its complexity, what we are going to finally get to is the Bayesian machine studying means of doing issues.

First, we’ll see if we will enhance conventional A/B testing with adaptive strategies. These all provide help to clear up the explore-exploit dilemma.

You’ll be taught about the epsilon-greedy algorithm, which you’ll have heard about within the context of reinforcement studying.

We’ll enhance the epsilon-greedy algorithm with an identical algorithm known as UCB1.

Finally, we’ll enhance each of these through the use of a totally Bayesian method.

Why is the Bayesian technique attention-grabbing to us in machine studying?

It’s a wholly completely different mindset about likelihood.

It’s a paradigm shift.

You’ll in all probability want to come back again to this course several instances earlier than it absolutely sinks in.

It’s additionally highly effective, and lots of machine-studying consultants typically make statements about how they “subscribe to the Bayesian school of thought”.

In sum – it’s going to provide us a variety of highly effective new instruments that we will use in machine studying.

The belongings you’ll be taught in this course usually are not solely relevant to A/B testing, however slightly, we’re utilizing A/B testing as a concrete instance of how Bayesian strategies might be utilized.

You’ll be taught these basic instruments of the Bayesian technique – using the instance of A/B testing – and then you definitely be capable of carrying these Bayesian strategies to extra superior machine studying fashions sooner or later.

See you in school!

“If you can’t implement it, you don’t understand it”

• Or as the good physicist Richard Feynman stated: “What I cannot create, I do not understand”.
• My programs are the ONLY programs the place you’ll learn to implement machine-studying algorithms from scratch
• Other programs will educate you on how you can plug your knowledge right into a library, however, do you really want to assist with 3 traces of code?
• After doing the identical factor with 10 datasets, you notice you didn’t be taught 10 issues. You discovered 1 factor, and simply repeated the identical 3 traces of code 10 instances…

Suggested Prerequisites:

• Probability (joint, marginal, conditional distributions, steady and discrete random variables, PDF, PMF, CDF)
• Python coding: if/else, loops, lists, dicts, units
• Numpy, Scipy, Matplotlib

 ↔

WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:

• Check out the lecture “Machine Learning and AI Prerequisite Roadmap” (out there within the FAQ of any of my programs, together with the free Numpy course)

Who this course is for:

• Students and professionals with a technical background who need to be taught Bayesian machine studying strategies to use to their knowledge of science work