Systems and methods for placing electronic advertisements
View Patent ↗This invention concerns optimal ad selection for Web pages by selecting and updating an attribute set, obtaining and updating an ad-attribute profile, and optimally choosing the next ad. The present invention associates a set of attributes with each customer. The attributes reflect the customers' interests and they incorporate the characteristics that impact ad selection. Similarly, the present invention associates with each ad an ad-attribute profile in order to calculate a customer's estimated ad selection probability and measure the uncertainty in that estimate. An ad selection algorithm optimally selects which ad to show based on the click probability estimates and the uncertainties regarding these estimates.
1. A computer-implemented method comprising:
establishing a customer profile for a customer, the customer profile including product attributes related to a product of interest to the customer;
computing, by at least one processor, a click probability estimate representing a likelihood that the customer will select an advertisement based on the advertisement and the product attributes of the customer profile;
determining, by the at least one processor, an uncertainty level of the click probability estimate, the uncertainty level being inversely proportional to a number of times the advertisement has been previously presented;
adjusting the click probability estimate based on the determined uncertainty level to calculate an uncertainty-adjusted click probability estimate;
causing the advertisement to be presented to the customer, over an electronic network, based on the uncertainty-adjusted click probability estimate;
receiving, over the electronic network, a response to the advertisement from the customer; and
reducing the uncertainty level associated with the uncertainty-adjusted click probability estimate based on the received response to the advertisement.
2. The computer-implemented method of claim 1 , further comprising:
adjusting the customer profile based on types of advertisements previously responded to by the customer.
3. The computer-implemented method of claim 1 , further comprising:
adjusting the customer profile based on Internet sites visited by the customer.
4. The computer-implemented method of claim 1 , wherein the response is a click selecting the advertisement.
5. The computer-implemented method of claim 1 , wherein the response is a request for more information.
6. The computer-implemented method of claim 1 , wherein the response is a purchase of an item.
7. A computer-implemented method comprising:
computing, by at least one processor, a click probability estimate representing a likelihood that a customer will select an advertisement;
determining, by the at least one processor, an uncertainty level of the click probability estimate, the uncertainty level being inversely proportional to a number of times the advertisement has been previously presented;
adjusting the computed click probability estimate based on the determined uncertainty level to calculate an uncertainty-adjusted click probability estimate; and
causing the advertisement to be presented to the customer, over an electronic network, based on the uncertainty-adjusted click probability estimate.
8. The computer-implemented method of claim 7 , further comprising:
receiving a response to the advertisement from the customer;
adjusting the click probability estimate for the advertisement based on the received response to the advertisement; and
reducing the uncertainty level of the uncertainty-adjusted click probability estimate based on the presentation of the advertisement.
9. The computer-implemented method of claim 7 , further comprising:
adjusting a customer profile based on types of advertisements previously responded to by the customer.
10. The computer-implemented method of claim 7 , further comprising:
adjusting a customer profile based on Internet sites visited by the customer.
11. The computer-implemented method of claim 8 , wherein the response is a click selecting the advertisement.
12. The computer-implemented method of claim 8 , wherein the response is a request for more information.
13. The computer-implemented method of claim 8 , wherein the response is a purchase of an item.
14. A computer-implemented method comprising:
computing, by at least one processor, a click probability estimate representing a likelihood that a customer will select an advertisement, and an uncertainty level of the click probability estimate, the uncertainty level being inversely proportional to a number of times the advertisement has been previously presented;
computing an uncertainty-adjusted click probability estimate by adjusting the computed click probability estimate based on the computed the uncertainty level;
causing the advertisement to be displayed to the customer, over an electronic network, based on the uncertainty-adjusted click probability estimate;
receiving, over the electronic network, a response to the advertisement from the customer; and
adjusting the uncertainty-adjusted click probability estimate for the advertisement based on the received response to the advertisement.
15. The computer-implemented method of claim 14 , further comprising:
adjusting a customer profile based on types of advertisements previously responded to by the customer, and Internet sites visited by the customer.
16. The computer-implemented method of claim 14 , further comprising:
providing a customer profile that includes category attributes related to a category of advertisements of interest to the customer and product attributes related to a product of interest to the customer.