A/B testing of a smartphone game

A/B testing of a smartphone game

Cookie Cats is an extremely popular mobile puzzle game developed by Tactile Entertainment. It is a classic puzzle game in which the player must connect tiles of the same color to clear the field and win the level. There are also singing cats.

As players progress through the game’s levels, they occasionally encounter gates that make them wait a certain amount of time or make in-app purchases to continue playing. In addition to encouraging in-app purchases, these gates serve the important purpose of giving players a forced break from the game, which will hopefully lead to increased and prolonged enjoyment of the game.

Obviously, gates are profitable for the developers of the game. However, where is the best place to put the gate? Originally, the first gates were placed at level 30. But maybe it’s better to put them later?

In this article, you will see a solution based on the AB test, in which the creators moved the first gate in Cookie Cats from level 30 to level 40. In particular, we will look at the impact of the A/B test on player retention. As usual, I will use Python and its libraries for A/B testing: numpy, pandas, scipy, statsmodels, matplotlib, seaborn, and others.


Leave a Reply

Your email address will not be published. Required fields are marked *