文档介绍：Computational Advertising
Andrei Broder
Yahoo! Research
Disclaimers
• This talk presents the opinions of the author. It does not
necessarily reflect the views of Yahoo! Inc or any other entity
• Algorithms, techniques, features, etc mentioned here might
or might not be in use by Yahoo! or any pany
- 2 -
What is “Computational Advertising”?
• New scientific sub-discipline, at the intersection of
– Large scale search and text analysis
– Information retrieval
– Statistical modeling
– Machine learning
– Classification
– Optimization
– Microeconomics
– mender systems
- 3 -
Computational advertising – main challenge
Find the "best match" between a
given user in a given context and a
suitable advertisement.
• Examples
– Context = Web search results Sponsored search
– Context = Publisher page Content match, banners
– Other contexts: mobile, video, newspapers, etc
• What is “best”???
- 4 -
Establishing a new discipline…
- 5 -
Establishing a new discipline…
- 6 -
Establishing a new discipline…
- 7 -
Establishing a new discipline…
Wolfram|Alpha isn't sure how
pute an answer from
your input
- 8 -
CACM
CACM, May 2009: http://mags./communications/200905/?pg=18
- 9 -
Key messages
1. Computational advertising = A principled way to find the
"best match" between a given user in a given context and a
suitable advertisement.
2. The financial scale putational advertising is huge
⇒ Trillions x milli-cents
⇒ Small constants matter, cost of serving matters
⇒ Expect plenty of further research
3. Advertising is a form of information.
⇒ Adding ads to a context is similar to the integration problem of
other types of information
⇒ Finding the “best ad” is a type of information retrieval problem
with multiple, possibly contradictory utility functions
4. New application domains and new techniques are
emerging every day
⇒ Good area for research + new businesses
- 10 -