A system and method select bids for a plurality of media plays, such as advertising spots on radio stations. Users provide bids for the medial plays and may select providers of the media plays and a time period of the media play. The media plays are associated with the bids. The bids are allocated to the media plays, and winning bids are selected.
1. A computer-implemented method for selecting bids for a plurality of media plays, the method comprising:
receiving, from a plurality of users by an auctioneer executed by one or more processors of a hub computer system, bids for a plurality of media plays;
determining the bids by a campaign manager executed by the one or more processors of the hub computer system, said determining comprising:
determining a target impression using a number of impressions in a target demographic group of a user's campaign;
determining an average cost per capita of the user's campaign;
generating a distribution multiplier configured to indicate how well a media play matches an impression distribution of the user's campaign, wherein generating the distribution multiplier, DM, comprises
calculating DM=DM 1 *DM 2 * . . . *DM N , where DM i is a distribution multiplier for the i th category from among N categories, where i=1, . . . , N, and N≧2, and
generating DM i comprises calculating DM i =1−(I impressions )/(S impressions ), where I impressions is a number of target impressions delivered by the i th category and S impressions is a total number of target impressions that the user's campaign expects the i th category to deliver; and
calculating a bid as a multiplicative product of the target impression, the average cost per capita and the distribution multiplier
associating media plays with the bids from the users; and
allocating the bids to the media play.
2. The computer-implemented method of claim 1 , wherein allocating the bids maximizes revenues from the bids.
3. The computer-implemented method of claim 1 , wherein allocating the bids is performed using integer programming.
4. The computer-implemented method of claim 1 , wherein the user comprises an advertiser.
5. The computer-implemented method of claim 1 , wherein allocating the bids increases a priority of a user receiving accepted bids in a previous auction less than a threshold.
6. The computer-implemented method of claim 1 , wherein allocating the bids maximizes impressions of the users.
7. The computer-implemented method of claim 1 , wherein allocating the bids complies with market campaign criteria of the users.
8. The computer-implemented method of claim 1 , wherein the bids are received one day before the play of the media play.
9. The computer-implemented method of claim 1 , wherein the bids are received on the same day as the play of the media play.
10. A computer storage medium encoded with a computer program for selecting bids for a plurality of media plays, the computer program comprising instructions that when executed by data processing apparatus cause the data processing apparatus to perform operations comprising:
receiving, from a plurality of users, bids for a plurality of media plays;
determining the bids, said determining operation comprising:
determining a target impression;
determining an average cost per capita of a campaign of a user;
generating a distribution multiplier, DM, wherein generating DM comprises
calculating DM=DM 1 *DM 2 * . . . *DM N , where DM i is a distribution multiplier for the i th category from among N categories, and
calculating DM i =1−(I impressions )/(S impressions ), where I impressions is a number of target impressions delivered by the i th category, and S impressions is to a total number of target impressions expected to be delivered by the i th category; and
calculating a bid as a multiplicative product of the target impression, the average cost per capita and the distribution multiplier;
associating media plays with the bids from the users; and
allocating the bids to the media play.
11. The computer-implemented method of claim 1 , wherein a category comprises a campaign geography.
12. The computer-implemented method of claim 1 , wherein a category comprises a criterion external to an auction.
13. The computer-implemented method of claim 12 , wherein the criterion external to the auction comprises one or more of weather conditions, current events and targeted responses.
14. A system for selecting bids for a plurality of media plays, the system comprising:
one or more hardware processors executing
an auctioneer configured to receive, from a plurality of users, bids for a plurality of media plays; and
a hardware processor executing a campaign manager communicatively coupled with the auctioneer, the campaign manager configured to determine the bids, wherein to perform a bid determination, the campaign manager is further configured to:
determine a target impression;
determine an average cost per capita of a campaign of a user;
generate a distribution multiplier, DM, where to generate DM, the campaign manager is configured to
calculate DM=DM 1 *DM 2 * . . . *DM N , where DM i is a distribution multiplier for the i th category from among N categories, and
calculate DM i =1−(I impressions )/(S impressions ), where I impressions is a number of target impressions delivered by the i th category, and S impressions is to a total number of target impressions expected to be delivered by the i th category; and
calculate a bid as a multiplicative product of the target impressions, the average cost per capita and the distribution multiplier;
the auctioneer is further configured to:
associate media plays with the bids from the users; and
allocate the bids to the media play.