Method and system for dynamic score floor modeling and application thereof
View Patent ↗The present teaching relates to dynamically generate a score floor model that provides a dynamically determined threshold metric to be used to select future bids that satisfy a first and second set of metrics. Feedback information is first received that relates to a plurality of bids previously submitted by a bidder to a publisher, wherein the feedback information indicates whether each of the plurality of bids has led to an impression. The first set of metrics specified by the publisher is obtained and the second set of metrics is retrieved. The score floor model with respect to the publisher is dynamically updated based on the feedback information as well as the first and second sets of metrics.
1. A method implemented on a computer having at least one processor, a storage, and a communication platform, comprising:
receiving, by the at least one processor via the communication platform, feedback information about a plurality of bids previously submitted by a bidder to a publisher, wherein the feedback information indicates whether each of the plurality of bids led to an impression;
obtaining, by the at least one processor, a first set of metrics specified by the publisher;
retrieving, by the at least one processor, a second set of metrics to be applied to the bidder; and
dynamically updating, by the at least one processor, a score floor model with respect to the publisher based on the feedback information as well as the first and second sets of metrics, wherein the score floor model is used to determine a dynamic threshold metric to be used to filter future bids to generate filtered future bids from which one or more of the filtered future bids that satisfy the first and second sets of metrics are selected.
2. The method of claim 1 , further comprising:
receiving, at the bidder, a bid request from the publisher;
identifying, by the bidder via the at least one processor, a set of candidate bids based on the bid request;
filtering the set of candidate bids based on the score floor model and the dynamic threshold metric to generate a selection pool of candidate bids;
selecting, from the selection pool of candidate bids, a response bid based on at least one criterion; and
transmitting the selected response bid to the publisher in response to the bid request.
3. The method of claim 2 , wherein identifying the set of candidate bids comprises:
generating a downstream bid solicitation request based on the bid request;
transmitting the downstream bid solicitation request to one or more downstream bidders associated with the bidder; and
receiving, from the one or more downstream bidders, the set of candidate bids.
4. The method of claim 2 , wherein identifying the set of candidate bids comprises:
generating an inventory candidate request based on the bid request;
transmitting the inventory candidate request to an inventory candidate bids selector; and
receiving, from the inventory candidate bids selector, the set of candidate bids.
5. The method of claim 1 , wherein the first set of metrics includes an impression rate, a response rate, or the impression rate and the response rate, wherein the impression rate and the response rate are specified with respect to the bidder.
6. The method of claim 1 , wherein the second set of metrics includes an expected level of revenue associated with the bidder.
7. The method of claim 1 , wherein the score floor model is dynamically updated in a batch mode or a derivative mode.
8. A system comprising at least one processor, storage, and a communication platform connected to a network, comprising:
a dynamic score floor model generator implemented by the at least one processor configured for dynamically generating a score floor model with respect to a publisher, wherein the score floor model is used to determine a dynamic threshold metric to be used to filter future bids to the publisher to generate filtered future bids from which one or more of the filtered future bids that satisfy a first set of metrics and a second set of metrics are selected; and
a score floor model based bid generator implemented by the at least one processor configured for identifying a response bid selected based on the score floor model in response to a bid request received from the publisher.
9. The system of claim 8 , wherein the dynamic score floor model generator comprises:
a feedback data analyzer configured for receiving feedback information about a plurality of bids previously submitted by a bidder to a publisher, wherein the feedback information indicates whether each of the plurality of bids led to an impression;
a publisher specific data aggregator configured for obtaining the first set of metrics specified by the publisher;
a publisher specific score floor model generator configured for:
retrieving the second set of metrics to be applied to the bidder;
dynamically updating the score floor model with respect to the publisher based on the feedback information, the first set of metrics, and the second set of metrics, wherein the updated score floor model is used to determine the dynamic threshold metric.
10. The system of claim 8 , wherein the score floor model based bid generator comprises:
a bid request analyzer configured for receiving and analyzing a bid request from the publisher;
a candidate bid solicitor configured for identifying a set of candidate bids based on the bid request;
a response bid selector configured for:
filtering the set of candidate bids based on the score floor model and the dynamic threshold metric to generate a selection pool of candidate bids,
selecting, from the selection pool of candidate bids, a response bid based on at least one criterion, and
transmitting the selected response bid to the publisher in response to the bid request.
11. The system of claim 10 , wherein the candidate bid solicitor is one of:
a downstream bid solicitor configured for soliciting the set of candidate bids from one or more downstream bidders; or
an inventory candidate requester configured for selecting the set of candidate bids from an inventory candidate bids selector.
12. The system of claim 8 , wherein the first set of metrics an impression rate, a response rate specified with respect to the bidder, or the impression rate and the response rate.
13. The system of claim 8 , wherein the second set of metrics includes an expected level of revenue associated with the bidder.
14. The system of claim 8 , wherein the dynamic score floor model generator dynamically updates the score floor model in a batch mode or a derivative mode.
15. A machine readable non-transitory medium having information stored thereon, wherein the information, when read by the machine, causes the machine to perform:
receiving feedback information about a plurality of bids previously submitted by a bidder to a publisher, wherein the feedback information indicates whether each of the plurality of bids led to an impression;
obtaining a first set of metrics specified by the publisher;
retrieving a second set of metrics to be applied to the bidder; and
dynamically updating a score floor model with respect to the publisher based on the feedback information as well as the first and second sets of metrics, wherein:
the score floor model is used to determine a dynamic threshold metric to be used to filter future bids to generate filtered future bids from which one or more of the filtered future bids that satisfy the first and second sets of metrics are selected.
16. The medium of claim 15 , wherein the information, when read by the machine, further causing the machine to perform:
receiving a bid request from the publisher;
identifying a set of candidate bids based on the bid request;
filtering the set of candidate bids based on the score floor model and the dynamic threshold metric to generate a selection pool of candidate bids;
selecting, from the selection pool of candidate bids, a response bid based on at least one criterion; and
transmitting the selected response bid to the publisher in response to the bid request.
17. The medium of claim 16 , wherein identifying the set of candidate bids comprises:
generating a downstream bid solicitation request based on the bid request;
transmitting the downstream bid solicitation request to one or more downstream bidders associated with the bidder; and
receiving, from the one or more downstream bidders, the set of candidate bids.
18. The medium of claim 16 , wherein identifying the set of candidate bids comprises:
generating an inventory candidate request based on the bid request;
transmitting the inventory candidate request to an inventory candidate bids selector; and
receiving, from the inventory candidate bids selector, the set of candidate bids.
19. The medium of claim 15 , wherein:
the first set of metrics includes an impression rate, a response rate specified with respect to the bidder, or the impression rate and the response rate; and
the second set of metrics includes an expected level of revenue associated with the bidder.
20. The medium of claim 15 , wherein the score floor model is dynamically updated in a batch mode or a derivative mode.