From the course: SQL for AI Projects: From Data Exploration to Impact

Unlock the full course today

Join today to access over 24,900 courses taught by industry experts.

A/B Testing in SQL: Conversion Rates and more

A/B Testing in SQL: Conversion Rates and more - SQL Tutorial

From the course: SQL for AI Projects: From Data Exploration to Impact

Start my 1-month free trial Buy for my team

A/B Testing in SQL: Conversion Rates and more

“

- [Instructor] In our final section, we'll implement a simple A/B test framework to analyze the performance and uplift in our AI experiment. We'll be using three tables for our analysis: sales, visits, and features. Our aim for our experimentation transformations is to generate a single table where we can inspect the sales behavior for a user after they've interacted with our AI search feature within our experiment timeframe. Once we have our base experiment_analysis_df table sorted, we can use this to answer some simple analysis questions by splitting our user groups into treatment versus control and calculating some simple metrics, such as visits, sales, and conversion rate. Next, we'll use our analysis metrics to perform an A/B hypothesis test. While these math formulas might look intimidating at first, once we break down each component, the analysis can be quite straightforward and insightful. We'll also go ahead and…

Contents