Web Performance Impacts Revenue: Velocity ’09 Highlights

Bookmark and Share

Jun ‘09 26

I just got back from Velocity, a new-ish (2nd one) performance & scalability/availability conference. Last year, a common complaint was a lack of presentations around “why speed matters” and this year they did not disappoint.

First, Google and Microsoft teamed up to present the results from experiments on the impact of performance on their search business:

bing search delay impact on performance

The Bing graph shows that just a 1/2 sec. delay before sending the search results had a -1.2% negative impact on revenue. A 2 second delay had a -2.1% impact.

google search delay impact on performance

Google slowed down their load progressively, and found that delaying 400ms after their header (logo, etc.) resulted in -0.59% less daily searches per users.

The next day, Marissa Meyer (VP, Google User Experience) gave a talk and revealed their historic findings:

google historical delay  impact on speed

They delayed results 400ms and searches/user decreased -0.44%, then to -0.76% after six weeks. After removing the delay, users did -0.21% fewer searches, hinting at an after-effect to speed. She noted this was “millions” in potential revenue that could be lost.

Shopzilla.com (shopping comparison search) made an optimization (much like we have done at AOL) to move their static images off the “*.shoppzilla.com” domain to avoid cookie pollution from the top level domain.
This tweak earned them a 0.5% top line revenue increase.

They went on to improve their performance from 4-6 seconds to 1.5 seconds, and had the following results to share:

shopzilla performance results from speed redesign

Conversion rates increased 7 to 12%. Page views increased 25%. They found Google rewarded them in search results for SEM (speed is an SEM quality factor) 8% increase in SEM visits in the U.S., and 120% in the U.K.

Dave Artz (yours truly) gave a talk on AOL’s secret weapons in optimization, and shared some new research he’s done with their internal tracking system’s data.

We took a sample of visits over the course of a day on various AOL sites, and calculated the average load time of the pages on each visit. We then broke the visits into percentile groups, the top 10th percentile being the fastest 10% of visits and the bottom 100th being the slowest 10%, and examined the Page Views within each visit group (fyi, refreshing photo galleries were not counted as page views):

aol speed impact on page views visit

The data showed that the visits with the fastest load times delivered the most page views, and degraded (sometimes quickly) as load times decreased. We found a clear correlation between faster/slower visits and page views.

Now you may be wondering, how do I get faster? IM me, we’ll talk about it. :)

Bookmark and Share

7 Responses to “Web Performance Impacts Revenue: Velocity ’09 Highlights”

  1. Stoyan voiced... June 26th, 2009 at 3:31 pm

    Nice summary, thanks Dave! It’s really important for more people to be aware of the stats.

  2. Nicole Sullivan reported... June 26th, 2009 at 6:48 pm

    This is an awesome write-up! I wish I’d realized you wrote it before I did mine… I could have just linked to it! :) It was great to meet you.


  3. Twitted by stubbornella thought out loud... June 26th, 2009 at 7:01 pm

    [...] This post was Twitted by stubbornella [...]

  4. Wim Leers twisted... June 27th, 2009 at 4:45 am

    Very interesting (and convincing) numbers. Thanks! :)

    (This is unfortunately just too late to add to my bachelor thesis.)

  5. Aaron Peters squawked... June 29th, 2009 at 1:56 am

    Nice summary Dave.

    The Shopzilla case is especially interesting, because of the SEM part: making load times faster can actually result in (a lot) more traffic from Google Adwords campaigns.

    Talk to you soon (mail/IM).


  6. EricGoldsmith.com » Blog Archive » Velocity Conference Wrap-up stuttered... July 6th, 2009 at 7:26 am

    [...] were serveral fantastic presentations from Google, Microsoft, and others. Steve, Brady, Nicole, and Dave have blogged about these results in detail (including links to the original presentations, and a [...]

  7. mattkime proclaimed... March 1st, 2010 at 12:50 pm

    hello dave,

    looking for a better way to reach you but this is the best i can do -

    i like your jQuery 1.3 cheat sheet and would like to offer help to upgrade it to version 1.4. drop me a line a mwk206@nyu.edu. hopefully my spam filter is up to this test.

Leave a Reply

Please index me, experiment!

“It’s called reading, you know, top to bottom, left to right. A group of words together is called a sentence. Take Tylenol for any headaches, Midol for any cramps.” — Richard Hayden