Difference between revisions of "Predicting ads' quality"
(New page: Internet advertising is the main source of income for search engines today. As the number of internet users increases, the internet advertising becomes more and more popular among people w...) |
|||
| Line 2: | Line 2: | ||
Impressed ads around search result pages in search engines are chosen with an auction. It means when a user enters a search query, an auction will be placed among all relevant ads and top ads will be chosen based on two factors: offered bid and quality. Search engines use the Price per Click (PPC) model for internet advertising, in this model if ad placed in search result page for a search query, advertisers should pay only if user clicks on the ad, and otherwise there is no cost for advertisers just because of ad impression. So for earning maximum revenue, search engines try to select ads with most quality which can attract more clicks. | Impressed ads around search result pages in search engines are chosen with an auction. It means when a user enters a search query, an auction will be placed among all relevant ads and top ads will be chosen based on two factors: offered bid and quality. Search engines use the Price per Click (PPC) model for internet advertising, in this model if ad placed in search result page for a search query, advertisers should pay only if user clicks on the ad, and otherwise there is no cost for advertisers just because of ad impression. So for earning maximum revenue, search engines try to select ads with most quality which can attract more clicks. | ||
| + | |||
| + | |||
| + | |||
| + | == People == | ||
| + | |||
| + | * [http://www.cs.sfu.ca/~mhefeeda/ Mohamed Hefeeda] | ||
| + | |||
| + | * [http://www.cs.sfu.ca/~hsadeghi/ Hamed Sadeghi Neshat (MSc student)] | ||
| + | |||
| + | |||
| + | |||
| + | == On-going Research Problems == | ||
The propose of current study is to investigate on a quality measurement method working with conceptual and feature based similarity algorithms which can find similar ads from historical data and estimate ads’ quality for new ads in compare with current ads in the Internet. More over, in this experiment we will examine some novel machine learning methods and use them in the internet and advertising concepts and try to customize them in order to be effective in these areas. | The propose of current study is to investigate on a quality measurement method working with conceptual and feature based similarity algorithms which can find similar ads from historical data and estimate ads’ quality for new ads in compare with current ads in the Internet. More over, in this experiment we will examine some novel machine learning methods and use them in the internet and advertising concepts and try to customize them in order to be effective in these areas. | ||
| + | |||
| + | |||
| + | |||
| + | == References and Links == | ||
Revision as of 14:22, 25 May 2010
Internet advertising is the main source of income for search engines today. As the number of internet users increases, the internet advertising becomes more and more popular among people who want to advertise a service or a product. Google reported it had 6,475 million dollars revenue from advertisement in 2009 which is 8% more than previous year, and it means internet advertising is a wide and attractive market for advertisers and search engines.
Impressed ads around search result pages in search engines are chosen with an auction. It means when a user enters a search query, an auction will be placed among all relevant ads and top ads will be chosen based on two factors: offered bid and quality. Search engines use the Price per Click (PPC) model for internet advertising, in this model if ad placed in search result page for a search query, advertisers should pay only if user clicks on the ad, and otherwise there is no cost for advertisers just because of ad impression. So for earning maximum revenue, search engines try to select ads with most quality which can attract more clicks.
People
On-going Research Problems
The propose of current study is to investigate on a quality measurement method working with conceptual and feature based similarity algorithms which can find similar ads from historical data and estimate ads’ quality for new ads in compare with current ads in the Internet. More over, in this experiment we will examine some novel machine learning methods and use them in the internet and advertising concepts and try to customize them in order to be effective in these areas.
