Systems and methods for web spike attribution
Systems and methods are disclosed that measure web activity bursts after ad broadcasts that may be sent to multiple persons. One system uses a cookie-less/cookie-optional, anonymous/personal-identification-not-required, method for web-based conversion tracking that will work on broadcast media systems such as television, and could also be applied to measuring spikes from email, radio, and other forms of advertising where an episodic ad event is broadcast to multiple parties, and where responses occur in a batch after the broadcast.
1. A computer-implemented method for web spike attribution, the method comprising:
filtering, by a server, website request data to include at least one of null referrers, previously-uncookied visitors, and traffic not having a search query referrer;
attributing, by the server, a change in the filtered website request data to a media event based on a calculated probability that the change in the filtered website request data is due to the media event; and
generating and displaying, by the server, a user interface element that represents attribution of the filtered website request data to the media event, and that indicates a number of website impressions or requests associated with the media event.
2. The method of claim 1 , further comprising:
determining, by the server, a number of impressions due to the media event based on the change in the filtered website request data; and
generating, by the server, a report on the change in the filtered website request data and the number of impressions.
3. The method of claim 2 , further comprising:
determining, by the server, a change in the filtered website request data per impressions performance based on media data for a plurality of media events including the media event, the media data including one or more of a network, a day, an hour, a program, and a geography for each media event; and
generating, by the server, a report on the change in the filtered website request data per impressions performance based on at least one of the network, the day, the hour, the program, and the geography.
4. The method of claim 1 , further comprising:
filtering, by the server, the filtered website request data to increase signal-to-noise based on an IP-geographic lookup to establish a geographic origin of website request traffic.
5. The method of claim 1 , further comprising:
determining, by the server, a number of impressions due to the media event based on the filtered website request data for a time period during the media event and the filtered website request data for a time period prior to the media event;
determining, by the server, a change in the filtered website request data per impressions performance based on media data for a plurality of media events including the media event, the media data including one or more of a network, a day, an hour, a program, and a geography for each media event; and
determining, by the server, a targeting score of the media event based on the number of impressions and the change in the filtered website request data per impressions.
6. The method of claim 5 , further comprising:
generating, by the server, a purchase recommendation based on the targeting score of the media event.
7. The method of claim 1 , further comprising:
determining, by the server, a number of impressions due to the media event based on the filtered website request data for a time period during the media event and the filtered website request data for a time period prior to the media event; and
determining, by the server, a change in the filtered website request data per impressions performance based on media data for a plurality of media events including the media event, the media data including a plurality of a network, a day, an hour, a program, and a geography for each media vent.
8. A system for web spike attribution, the system comprising:
a data storage device that stores instructions for web spike attribution; and
a processor configured to execute the instructions to perform a method including:
filtering website request data to include at least one of null referrers, previously-uncookied visitors, and traffic not having a search query referrer;
attributing a change in the filtered website request data to a media event based on a calculated probability that the change in the filtered website request data is due to the media event; and
generating and displaying a user interface element that represents attribution of the filtered website request data to the media event, and that indicates a number of website impressions or requests associated with the media event.
9. The system of claim 8 , wherein the processor is further configured to execute the instructions to perform the method including:
determining a number of impressions due to the media event based on the change in the filtered website request data; and
generating a report on the change in the filtered website request data and the number of impressions.
10. The system of claim 9 , wherein the processor is further configured to execute the instructions to perform the method including:
determining a change in the filtered website request data per impressions performance based on media data for a plurality of media events including the media event, the media data including one or more of a network, a day, an hour, a program, and a geography for each media event; and
generating a report on the change in the filtered website request data per impressions performance based on at least one of the network, the day, the hour, the program, and the geography.
11. The system of claim 8 , wherein the processor is further configured to execute the instructions to perform the method including:
filtering the change in the filtered website request data to increase signal-to-noise based on an IP-geographic lookup to establish a geographic origin of website request traffic.
12. The system of claim 8 , wherein the processor is further configured to execute the instructions to perform the method including:
determining a number of impressions due to the media event based on the change in the filtered website request data for a time period during the media event and the change in the filtered website request data for a time period prior to the media event;
determining a change in the filtered website request data per impressions performance based on media data for a plurality of media events including the media event, the media data including one or more of a network, a day, an hour, a program, and a geography for each media event; and
determining a targeting score of the media event based on the number of impressions and the change in the filtered website request data per impressions.
13. The system of claim 12 , wherein the processor is further configured to execute the instructions to perform the method including:
generating, a purchase recommendation based on the targeting score of the media event.
14. The system of claim 8 , wherein the processor is further configured to execute the instructions to perform the method including:
determining a number of impressions due to the media event based on the filtered website request data for a time period during the media event and the filtered website request data for a time period prior to the media event; and
determining a filtered website request data per impressions performance based on media data for a plurality of media events including the media event, the media data including a plurality of a network, a day, an hour, a program, and a geography for each media event.
15. A non-transitory machine-readable medium storing instructions that, when executed by a computing system, causes the computing system to perform a method for web spike attribution, the method including:
filtering website request data to include at least one of null referrers, previously-uncookied visitors, and traffic not having a search query referrer;
attributing a identified change in the filtered website request data to a media event based on a calculated probability that the change in the filtered website request data is due to the media event; and
generating and displaying a user interface element that represents attribution of the filtered website request data to the media event, and that indicates a number of website impressions or requests associated with the media event.
16. The non-transitory machine-readable medium of claim 15 , the method further comprising:
determining a number of impressions due to the media event based on the change in the filtered website request data; and
generating a report on the change in the filtered website request data and the number of impressions.
17. The non-transitory machine-readable medium of claim 15 , the method further comprising:
filtering the filtered website request data to increase signal-to-noise based on an IP-geographic lookup to establish a geographic origin of website request traffic.
18. The non-transitory machine-readable medium of claim 15 , the method further comprising:
determining a number of impressions due to the media event based on the filtered website request data for a time period during the media event and the filtered website request data for a time period prior to the media event;
determining, a change in the filtered website request data per impressions performance based on media data for a plurality of media events including the media event, the media data including one or more of a network, a day, an hour, a program, and a geography for each media event; and
determining a targeting score of the media event based on the number of impressions and the change in the filtered website request data per impressions.
19. The non-transitory machine-readable medium of claim 18 , the method further comprising:
generating a purchase recommendation based on the targeting score of the media event.
20. The non-transitory machine-readable medium of claim 15 , the method further comprising:
determining a number of impressions due to the media event based on the filtered website request data for a time period during the media event and the filtered website request data for a time period prior to the media event; and
determining a change in the filtered website request data per impressions performance based on media data for a plurality of media events including the media event, the media data including a plurality of a network, a day, an hour, a program, and a geography for each media event.