Skip to content
Experimentation Wiki

What is A/B testing?

A/B testing, or split testing, is a method of comparing two or more versions of a website, feature, or experience to identify which one performs better. Users are randomly assigned to different versions—Control (the original) and Variant (the change)—and key metrics are measured to determine impact.

Below you see Group A for the Control with 50% traffic split and Group B for the variant with 50% traffic. As the image suggests, Group B had a higher Conversion Rate.

drawing

Key Elements:

  • Variants: Different versions of the same feature.

  • Randomisation: Users are split randomly to avoid bias.

  • Metrics: Performance indicators like conversion rate, click-through rate, or revenue.

  • Hypothesis-driven: Tests start with a prediction like “A shorter form will increase sign-ups.”

This approach is based on real user behavior, not opinions or assumptions.