DISQUS

DISQUS Hello! 20bits is using DISQUS, a powerful comment system, to manage its comments. Learn more.

Community Page

20bits

Jump to original thread »
Author

The Dangers of Genetic Optimization

Started by Jesse Farmer · 7 months ago

The guys at Weebly just had a round of press for their latest product, SnapAds, an ad optimization platform that uses genetic algorithms.


It's possible to apply these techniques to your website at large, but there are risks involved in automatic too much of the product devel ... Continue reading »

5 comments

  • Jamaal

    7 months ago

    Or can you apply it properly to this one? The world isn't linear, and combinations still matter.
    reply
  • gregdingle

    7 months ago

    Hi Jesse, the black box aspect of genetic algorithms can definitely be a drawback. I've just launched genetify as an open-source project.

    http://github.com/gregdingle/genetify/wikis/home

    I'm hoping people will incorporate different testing and optimization algorithms into it -- ANOVA, bayesian, GA -- so you can pick one to suit your purpose.
    reply
  • Jesse Farmer

    7 months ago

    Greg,

    Very cool. I'll keep an eye out.

    I'd love to meet up some time. You're in SF, right? Are you ever down in the peninsula?
    reply
  • Someone

    2 months ago

    "There's no learning"? From a business point of view, there is. You found a way to increase revenues with little effort. That trick is worth remembering.
    reply
  • Jesse Farmer

    2 months ago

    My point was that you didn't learn anything about your customers that can be applied in a different tactical situation. You don't know anything about their motivations, their interests, or their state of mind.

    So, although you get one result (increased revenue) you also lose something of value (verifiable knowledge about your customers). There's a tradeoff there, and perhaps you're willing to make it.
    reply

Add New Comment

Returning? Login