CIRCA:A/B Testing
From CIRCA
(Created page with '== Definition == An experimental approach to web design (especially user experience design), which aims to identify changes to web pages that increase or maximize an outcome of …') |
|||
Line 10: | Line 10: | ||
[[IMage: Conversion_rate.png|425px|thumb|left]] | [[IMage: Conversion_rate.png|425px|thumb|left]] | ||
<br><br><br><br> | <br><br><br><br> | ||
+ | |||
+ | == Examples == | ||
+ | |||
+ | A/B Testing on eBay: | ||
+ | [[IMage: Comparison.png|500px|thumb|left]]<br><br><br><br><br><br><br><br><br><br><br><br><br> | ||
+ | [http://www.youtube.com/watch?feature=player_embedded&v=oy89HnIJsE4 Video: How A/B Testing tools work (Visual Website Optimizer)] | ||
+ | |||
== Procedure == | == Procedure == | ||
Line 44: | Line 51: | ||
*[https://developer.amazon.com/sdk/ab-testing.html Amazon A/B Testing]<br> | *[https://developer.amazon.com/sdk/ab-testing.html Amazon A/B Testing]<br> | ||
*ABinator | *ABinator | ||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
== References == | == References == |
Revision as of 18:23, 24 March 2013
Contents |
Definition
An experimental approach to web design (especially user experience design), which aims to identify changes to web pages that increase or maximize an outcome of interest. (Wikipedia)
A/B Testing is a simple way to test changes to your page against the current design and determine which ones produce positive result. It is a method to validate that any new design or change to an element on your webpage is improving your conversion rate before you make that change to your site code. (Optimizely: What is A/B Testing)
Conversion Rate
In internet marketing, the conversion rate is the proportion of visitors to a website who take action to go beyond a casual content view or website visit, as a result of subtle or direct requests from marketers, advertisers, and content creators.
Examples
A/B Testing on eBay:
Video: How A/B Testing tools work (Visual Website Optimizer)
Procedure
- Determine a target
- Come up with hypothesis of factors
- Build a variation page
- Show the two pages randomly to users. Compare conversion rate of both sites.
Tips
- Test your software: Before you do the A/B testing, do an A/A testing first.
- Focus on one goal per page: More than one goal will mix the testing result.
- Test small elements: Small elements can also bring amazing conversion rate.
- Do not expect large results from small changes: If all testing results are not satisfying, maybe it is time to change the whole interface. A/B testing is not omnipotence for developing conversion rate.
- A/B Testing has its limitations: It only gives data, reasons are not included.
Companies well-known for using A/B Testing
- Amazon.com
- BBC
- eBay
- Microsoft
- LogMeln
- Netflix
- Platdom
- Vegas.com
- Zynga
A/B Testing Tools
References
Wikipedia: A/B Testing
Optimizely: What is A/B Testing
23 tips on how to A/B testing like a badass
Bella Martin, Bruce Hanington. (2012). Universal Methods of Design. Rockport Publishers.
ABTests.com
Seven A/B testing mistakes you need to stop making in 2013
Wikipedia: Conversion rate