From the course: Business Analytics Foundations: Predictive, Prescriptive, and Experimental Analytics
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
EXA use case
From the course: Business Analytics Foundations: Predictive, Prescriptive, and Experimental Analytics
EXA use case
- [Instructor] Let us try to design an experiment now for the email campaign's use case. The hypothesis we are trying to test is do users convert the same, whether the discount is 30% or 40%? So, here is the data we see on a yearly overall basis. For customers with earnings in the range 100 to 150K, the conversion at 30% simply be higher than when it is at 40%. So, does this mean that we can provide less discounts to this group of customers and yet convert at the same level? Or is this number more a fluke and not sustainable? Let us do an experiment. We will do A/B testing to confirm the validity of whether customers convert the same at 30% and 40%. We choose two subsets A and B of customers who earn in the range 100 to 150K. Subset A will be targeted with the campaign of 30% discounts and subset B will be targeted with the campaign of 40% discounts. We have to ensure that each subset has equal distribution of other variables like age and gender. We will execute both campaigns on the…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.