System and method to determine the validity of an interaction on a network
View Patent ↗The methods and systems of the invention utilize limited data to yield information about the validity of any given interaction with a website. Once validity information is available, an operator can determine whether or not to continue offering interactions to a given user. The determination could also relate to whether to report website interaction statistics based on undesired interactions, how to handle billing or payment for such undesired interactions, and what type of content to send to users who are interacting with the website in an undesirable manner.
1. A computer-implemented method of identifying a possible illegitimate interaction of a presumed user on a network, the method comprising:
generating by the user an interaction on network;
collecting data from the interaction, the data including aggregate measure data and unique feature data;
applying a predictive model to the aggregate measure data and the unique feature data to result in a risk value of a click interaction on the Internet, wherein the predictive model is built based on previously collected data, the previously collected data being collected from previous interactions and including previous aggregate measure data and previous unique feature data from the previous interactions;
determining a validity of the interaction based on the risk value;
saving the risk value in a database; and
charging an advertiser in accordance with the generated interaction on the network and based on the determined validity of the interaction.
2. The method according to claim 1 wherein the predictive model is based on at least one approach selected from the group comprising:
a probabilistic approach; and
a stochastic approach.
3. The method according to claim 1 wherein the step of collecting data includes collecting data on a number of clicks per network address in a given time period.
4. The method according to claim 1 wherein the step of collecting data includes collecting data relating to a number of unique queries per user session.
5. The method according to claim 1 wherein the step of collecting data includes collecting data on a number of network clicks for a given time period.
6. The method according to claim 1 wherein the step of collecting data includes collecting data on a number of distinct referral partners who could access the network.
7. The method according to claim 1 wherein the step of collecting data includes at least one step selected from the group comprising:
collecting data on an origin of the presumed user;
collecting data on a time of the interactions;
collecting data on a type of the interactions; and
collecting data on presumed measures of uniqueness of the presumed user.
8. The method according to claim 1 wherein the interaction comprises following a link to a website of the advertiser.
9. A computer-implemented method of rating a user interaction on a network, the method comprising:
generating by the user an interaction on network;
collecting data from the interaction, the data including aggregate measure data and unique feature data;
applying a predictive model to the aggregate measure data and the unique feature data to result in a risk value for a click interaction on the Internet, wherein the predictive model is built based on previously collected data, the previously collected data being collected from previous interactions and including previous aggregate measure data and previous unique feature data from the previous interactions;
rating the interaction based on the risk value;
saving the risk value in a database; and
charging an advertiser in accordance with the generated interaction on the network and based on the rating of the interaction.
10. The method according to claim 9 wherein the predictive model is based on at least one approach selected from the group comprising:
a probabilistic approach; and
a stochastic approach.
11. The method according to claim 9 wherein the step of collecting data includes collecting data on a number of clicks per network address in a given time period.
12. The method according to claim 9 wherein the step of collecting data includes collecting data relating to a number of unique queries per user session.
13. The method according to claim 9 wherein the step of collecting data includes collecting data on a number of network clicks for a given time period.
14. The method according to claim 9 wherein the step of collecting data includes collecting data on a number of distinct referral partners who could access the network.
15. The method according to claim 9 wherein the step of collecting data includes at least one step selected from the group comprising:
collecting data on an origin of the presumed user;
collecting data on a time of the interactions;
collecting data on a type of the interactions; and
collecting data on presumed measures of uniqueness of the presumed user.
16. The method according to claim 9 wherein the interaction comprises following a link to a website of the advertiser.
17. A system for detecting a possibly fraudulent interaction in a pay-for-placement search engine, the system comprising:
at least one interaction with the pay-for-placement search engine being generated by a user;
a first processor for collecting aggregate measure data and unique feature data about the interaction; and
a second processor for applying a predictive model to the aggregate measure data and unique feature data to result in a risk value for a click interaction on the Internet, wherein the predictive model is built based on previously collected data, the previously collected data being collected from previous interactions and including previous aggregate measure data and previous unique feature data from the previous interactions, wherein the a legitimacy of the interaction is determined based on the risk value, and wherein an advertiser is charged in accordance with the at least one interaction with the search engine and based on the risk value for the interaction.
18. The system according to claim 17 wherein the predictive model is based on at least one approach selected from the group comprising:
a probabilistic approach; and
a stochastic approach.
19. The system according to claim 17 wherein the first processor collects data on a number of clicks per network address in a given time period.
20. The system according to claim 17 wherein the first processor collects data relating to a number of unique queries per user session.
21. The system according to claim 17 wherein the first processor collects data on a number of network clicks for a given time period.
22. The system according to claim 17 wherein the first processor collects data on a number of distinct referral partners who could access the network.
23. The system according to claim 17 wherein the first processor collects data by performing at least one step selected from the group comprising:
collecting data on an origin of the presumed user;
collecting data on a time of the interactions;
collecting data on a type of the interactions; and
collecting data on presumed measures of uniqueness of the presumed user.
24. The system according to claim 17 wherein the interaction comprises a user following a link to a website of the advertiser.