https://github.com/taquynhnga2001/ab-testing-cookie-cats
Hypothesis Testing: Validate the result of an A/B Test for a mobile game company Cookie Cats
https://github.com/taquynhnga2001/ab-testing-cookie-cats
ab-testing hypothesis-testing python scipy statistics
Last synced: 3 months ago
JSON representation
Hypothesis Testing: Validate the result of an A/B Test for a mobile game company Cookie Cats
- Host: GitHub
- URL: https://github.com/taquynhnga2001/ab-testing-cookie-cats
- Owner: taquynhnga2001
- Created: 2025-01-03T18:27:21.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-01-04T08:38:06.000Z (over 1 year ago)
- Last Synced: 2025-03-27T21:34:00.263Z (over 1 year ago)
- Topics: ab-testing, hypothesis-testing, python, scipy, statistics
- Language: Jupyter Notebook
- Homepage:
- Size: 606 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# A/B Testing Project: Cookie Cats
## Introduction to A/B Testing
A/B testing, also known as split testing, is a statistical method used to compare two versions of a variable to determine which performs better in achieving a specific goal. By splitting a target audience into two groups, A (control group) and B (treatment group), each group is exposed to a different version of the variable. Metrics of interest, such as user engagement or retention, are then measured to evaluate the effectiveness of each variation. This technique is widely applied in industries like marketing, product development, and gaming to make data-driven decisions that enhance user experience and business outcomes.
## Project Background: Cookie Cats
Cookie Cats, developed by Tactile Entertainment, is a highly engaging mobile puzzle game where players connect tiles of the same color to progress through levels. The game features unique elements such as singing cats, which add charm and fun to the gameplay.

To encourage in-app purchases and enhance player engagement, Cookie Cats incorporates "gates" at certain levels. These gates require players to either wait for a specified period or make a purchase to proceed further. Initially, the first gate was set at level 30.
In this project, I will walk you through how we can conduct an A/B test to explore the impact of moving the first gate from level 30 to level 40. By analyzing player retention data, we aim to understand whether this adjustment improves player experience and engagement, providing insights into optimal gate placement strategies.