Restructuring AB testing processes

My client wanted to restructure the AB testing processes, as their previous setup was cumbersome, with very long experiment runtime and development time and limited insights on the full impact. l impact of the test. The main goal was to , with very long experiment runtime and development time and limited insights on the full impact. l impact of the test. The main goal was to improve test result quality and enhance data-driven decision-making.

Together with main stakeholders defined a new framework for AB testing

Identified seasonality and peak periods, based on which I created an ideal testing calendar

Introduced a roadmap for AB testing, where different departments could synchronize their testing plans, avoiding running similar test at the same time, and giving enough time for the teams to define the scopes once several tests needed to run simultaneously

Convinced the company to involve data analysts from the early stages of the planning phase

Worked in cross-functional teams, defined new events scopes, enabling the company to monitor the whole performance of their tests

Worked together with developers, providing them event specifications and QA-ing the implemented events

Implemented all analytics events into the datawarehouse using Google Tag Manager

Automated the analysis process using Python

Provided monetization summaries and strategic recommendations based on the AB tests to C-levels.

Decreased the necessity of running AB test separately on all platforms

Improved test result quality by introducing AB testing roadmap and synchronizing the plans of different departments

In the course of 1 year, set up 40+ A/B tests in Amplitude, Google Optimize and Google Firebase which led to an overall increase of conversion rate by 7% among our key user groups, and improved overall user retention by 15%