US 8,527,339 B2Granted

Quality based pricing and ranking for online ads

AssigneeMicrosoft Corporation

InventorsAsela J. Gunawardana, Jody D. Biggs, Jesper B. Lind, Christopher A. Meek

Life of this patent

Estimating the term…

Loading patent…

Abstract

A “Quality-Based Ad Pricer” prices ads as a function of how users respond to a particular page and/or domain to which they are sent by an online advertisement. User experience is improved by ensuring that advertisements that are more relevant to a user are priced less than an ads which are less relevant to the user. In particular, a quality factor for each ad is determined as a property of the advertiser's site based on measured user behaviors with respect to that site. This quality factor is then used in ranking, selecting, and pricing ads in an automated online auction. Further, while ad aggregators are not excluded from the ad market by the pricing rules of the Quality-Based Ad Pricer, these rules ensure that there is a “level playing field” such that ads of merchants are not excluded by the ads of ad aggregators.

Claims17

Dependent claims

A method for selecting and determining per-click prices for online advertisements via an automated auction, comprising steps for:

using a computing device for:
receiving one or more advertiser bids and one or more corresponding advertisements from each of a plurality of advertisers;
receiving statistical information characterizing behavior of a plurality of users with respect to each advertisement, wherein the statistical information for each advertisement includes an ad click count that indicates a number of times an ad landing page is reached by clicking the advertisement on a search results page of a search engine, and a redirect count that indicates a number of times a URL redirect is used to change a domain of the ad landing page to a different domain following clicking the advertisement on the search results page of a search engine;
computing a quality factor for each advertisement as a function of the statistical information by dividing the ad click count by a sum of the redirect count and the ad click count;
computing a payment probability for each advertisement as a function of the statistical information;
sorting the advertisements in decreasing order of an effective bid that is a function of the quality factor, the payment probability, and the advertiser bid;
selecting a number of the top sorted advertisements for display in a corresponding number of available ad slots, wherein the ad slots have a range of most desirable to least desirable, and wherein the selected advertisements are assigned to the ad slots in direct order of sort and desirability, so that the top sorted advertisement is assigned to the most desirable ad slot;
and
computing a price for each selected ad.

6 more elements

A system for selecting and pricing online advertisements in an automated online auction, comprising:

a device for receiving a maximum bid price corresponding to one or more specific advertisements from each of a plurality of advertisers;
a device for receiving statistical information characterizing behavior of one or more users with respect to each unique advertisement;
a device for computing a quality factor for each advertisement as a function of the statistical information collected for the users by dividing an advertisement click count included in the statistical information by a sum of the advertisement click count and a redirect count included in the statistical information;
a device for computing a payment probability for each advertisement;
a device for sorting the advertisements from highest to lowest relative to an effective bid computed for each advertisement as a function of the quality factor of each advertisement, the payment probability of each advertisement, and the maximum bid associated with each advertisement;
a device for selecting a number of the highest sorted advertisements corresponding to a number of available ad slots;
and
a device for computing a price for each selected advertisement.

5 more elements

A computer-readable medium having computer executable instructions stored therein for selecting and pricing online advertisements in an automated online advertisement auction relative to one or more keywords, said instructions comprising:

receiving one or more advertisements from each of a plurality of advertisers, each advertisement having one or more corresponding maximum bids;
receiving statistical information characterizing behavior of a plurality of users with respect to the advertisements;
computing a quality factor for each advertisement as a function of the statistical information by dividing an advertisement click count included in the statistical information by a sum of the advertisement click count and a redirect count included in the statistical information;
determining a payment probability for each advertisement as a function of a type of advertisement pricing model being used;
computing an effective bid for each advertisement as a function of the quality factor of each advertisement, the payment probability of each advertisement, and the corresponding maximum bid associated with each advertisement;
ranking the advertisements in an order of highest to lowest effective bid;
determining a number of available ad slots, said ad slots having a ranking of highest to lowest desirability;
selecting a number of highest ranked advertisements corresponding to the number of available ad slots and assigning the selected advertisements to the available ad slots with higher ranked advertisements being assigned in rank order to higher ranked ad slots;
and
computing a price for each selected advertisement using pricing rules corresponding to the automated online advertisement auction.

7 more elements

Dependencies are inferred from the claim text.