Похожие презентации:
Stanford Data Mining
1. Greg Linden
Make Data UsefulGreg Linden
2.
“[Help] people find anddiscover anything they
want to buy online”
- Jeff Bezos
3.
Help people find anddiscover anything
online
4.
“Encourage experimentation... as much of it as possible”
- Jeff Bezos
5.
What is the goal?Revenue
Clicks
Visitors
Retention
Traffic
Time on site
Customer acquisition
6.
MeasureLearn
Optimize
Iterate
7.
“Worry about the data firstbefore you worry about the
algorithm”
- Peter Norvig
8.
[Banko andBrill, 2001]
9.
On the design ofrecommendation
features
10.
Design to encourageforgiveness of mistakes
11.
Help when help is wanted12.
“Discovery is when somethingwonderful that you didn't know
existed, or didn't know how to
ask for, finds you.”
- Fortune Magazine
13.
Discovery of the newand surprising using
the recent
14.
“Users really respond tospeed.”
- Marissa Mayer
15.
+500 ms-20% traffic
+100 ms
@ Amazon
-1% sales
16.
Speed matters!17.
• Measure, then optimize toward a goal• Big data first, then algorithms
• Encourage users to forgive you
• Help when help is wanted
• Surprise and focus on the new
• Speed matters