Database Reference
In-Depth Information
(1) Some sites, such as eBay, Craig's List or auto trading sites allow advertisers to post
their ads directly, either for free, for a fee, or a commission.
(2) Display ads are placed on many Web sites. Advertisers pay for the display at a fixed
rate per
impression
(one display of the ad with the download of the page by some
user). Normally, a second download of the page, even by the same user, will result in
the display of a different ad and is a second impression.
(3) On-line stores such as Amazon show ads in many contexts. The ads are not paid for
by the manufacturers of the product advertised, but are selected by the store to max-
imize the probability that the customer will be interested in the product. We consider
this kind of advertising in
Chapter 9
.
(4) Search ads are placed among the results of a search query. Advertisers bid for the right
to have their ad shown in response to certain queries, but they pay only if the ad is
clicked on. The particular ads to be shown are selected by a complex process, to be
discussed in this chapter, involving the search terms that the advertiser has bid for, the
amount of their bid, the observed probability that the ad will be clicked on, and the
total budget that the advertiser has offered for the service.
8.1.2
Direct Placement of Ads
When advertisers can place ads directly, such as a free ad on Craig's List or the “buy it
now” feature at eBay, there are several problems that the site must deal with. Ads are dis-
played in response to query terms, e.g., “apartment Palo Alto.” The Web site can use an
inverted index of words, just as a search engine does (see
Section 5.1.1
)
and return those
ads that contain all the words in the query. Alternatively, one can ask the advertiser to spe-
cify parameters of the ad, which are stored in a database. For instance, an ad for a used
car could specify the manufacturer, model, color, and year from pull-down menus, so only
clearly understood terms can be used. Queryers can use the same menus of terms in their
queries.
Ranking ads is a bit more problematic, since there is nothing like the links on the Web
to tell us which ads are more “important.” One strategy used is “most-recent first.” That
strategy, while equitable, is subject to abuse, where advertisers post small variations of
their ads at frequent intervals. The technology for discovering ads that are too similar has
already been covered, in
Section 3.4
.
An alternative approach is to try to measure the attractiveness of an ad. Each time it is
displayed, record whether or not the queryer clicked on it. Presumably, attractive ads will
be clicked on more frequently than those that are not. However, there are several factors
that must be considered in evaluating ads:
