# Conversion Rate Optimization through Evolutionary Computation

## TL;DR

This paper introduces Sentient Ascend, an evolutionary computation system for web interface conversion rate optimization that outperforms human-designed interfaces by leveraging parallel online evaluation and discovering complex interactions.

## Contribution

It presents a novel evolutionary optimization system for web design that enables massively multivariate testing with real user interactions, surpassing traditional manual methods.

## Key findings

- Over 43% improvement in conversion rate achieved
- Enables discovery of complex interactions between design elements
- Demonstrates effectiveness through a real-world media site case study

## Abstract

Conversion optimization means designing a web interface so that as many users as possible take a desired action on it, such as register or purchase. Such design is usually done by hand, testing one change at a time through A/B testing, or a limited number of combinations through multivariate testing, making it possible to evaluate only a small fraction of designs in a vast design space. This paper describes Sentient Ascend, an automatic conversion optimization system that uses evolutionary optimization to create effective web interface designs. Ascend makes it possible to discover and utilize interactions between the design elements that are difficult to identify otherwise. Moreover, evaluation of design candidates is done in parallel online, i.e. with a large number of real users interacting with the system. A case study on an existing media site shows that significant improvements (i.e. over 43%) are possible beyond human design. Ascend can therefore be seen as an approach to massively multivariate conversion optimization, based on a massively parallel interactive evolution.