Can A/B testing get a lot smarter with machine learning?

This article is about the launch of a new SaaS offering called Synference. It is a combination of machine learning and A/B testing. In a nutshell, it will run your A/B tests through their API and use basic user data garnered from IP addresses and user agents to help you make decisions about what to charge your customers or clients. As the API receives user feedback -- was the banner clicked, did the customer pay, etc -- Synference detects patterns of user behavior and updates its statistical model accordingly.