Preservation of scores of the quality of traffic to network sites across clients and over time
A software and/or hardware facility for scoring the quality of traffic to a site accessible via the Internet or other network. The facility may generate training set data and use the training set data to identify parameters indicative of fraudulent traffic to a site and reduce the effect of fraudulent traffic advertisers and publishers. The facility may score the quality of traffic and determine combinations of parameters that are indicative of the quality of traffic to the site. Traffic to the site may be scored based on the combination of parameters associated with the one or more sessions. Lower scores are indicative of traffic having little value to a publisher, advertiser, or third party; higher scores are indicative of traffic having greater value.
1 . A method comprising:
receiving, by a computer system comprising one or more hardware processors, a first set of data that identifies a first plurality of clicks by a first set of devices interacting via a network environment with an advertisement displayed on a publisher website, and a second set of data that identifies a second plurality of clicks by a second set of devices interacting via the network environment with the advertisement displayed on the publisher website, wherein each click of the first plurality of clicks and the second plurality of clicks is associated with a combined identifier that includes: (i) a device identifier of a device of the first set of devices or the second set of devices; and (ii) at least two bytes of an IP address associated with the device identifier;
receiving, by the computer system, a first set of rules that is applied to one or more first parameters associated with the first set of data and a second set of rules that is applied to one or more second parameters associated with the second set of data, wherein:
the first parameters are used to estimate a first value representing characteristics associated with the first plurality of clicks performed by the first set of devices; and
the second parameters are used to estimate a second value representing characteristics associated with the second plurality of clicks performed by the second set of devices;
identifying, by the computer system, one or more overlapping rules that exist in both the first set of rules and the second set of rules, wherein each rule of the one or more overlapping rules is configured to: (i) process the first parameters to estimate the first value; and (ii) process the second parameters to estimate the second value;
applying, by the computer system, the one or more overlapping rules to the first set of data to estimate the first value;
applying, by the computer system, the one or more overlapping rules to the second set of data to estimate the second value, wherein applying the one or more overlapping rules includes, for each combined identifier:
measuring a velocity metric between at least two consecutive clicks associated with the combined identifier,
determining an elapsed time during which the device associated with the combined identifier interacted with the advertisement; and
assigning values to clicks associated with the combined identifier based at least in part on the velocity metric and the elapsed time;
processing, by the computer system, the first value and the second value to estimate a correction factor;
using, by the computer system, the correction factor to normalize the first value to generate a normalized first value; and
using, by the computer system, the correction factor to normalize the second value to generate a normalized second value so that the first value and the second value are on a same scale.
2 . The method of claim 1 , wherein the first set of data and the second set of data are received from a server log.
3 . The method of claim 1 , wherein assigning a value to the clicks is further based on IP addresses associated with the clicks.
4 . The method of claim 1 , wherein:
the values indicate quality of the clicks; and
higher quality clicks are indicative of network traffic having desirable characteristics.
5 . The method of claim 1 , wherein:
the values indicate quality of the clicks; and
lower quality clicks are indicative of fraudulent, likely fraudulent, or otherwise non-productive network traffic.
6 . A system comprising:
one or more data processors; and
a non-transitory computer readable storage medium containing instruction which, when executed on the one or more data processors, cause the one or more data processors to perform one or more operations including:
receiving, by a computer system comprising one or more hardware processors, a first set of data that identifies a first plurality of clicks by a first set of devices interacting via a network environment with an advertisement displayed on a publisher website, and a second set of data that identifies a second plurality of clicks by a second set of devices interacting via the network environment with the advertisement displayed on the publisher website, wherein each click of the first plurality of clicks and the second plurality of clicks is associated with a combined identifier that includes: (i) a device identifier of a device of the first set of devices or the second set of devices; and (ii) at least two bytes of an IP address associated with the device identifier;
receiving, by the computer system, a first set of rules that is applied to one or more first parameters associated with the first set of data and a second set of rules that is applied to one or more second parameters associated with the second set of data, wherein:
the first parameters are used to estimate a first value representing characteristics associated with the first plurality of clicks performed by the first set of devices; and
the second parameters are used to estimate a second value representing characteristics associated with the second plurality of clicks performed by the second set of devices;
identifying, by the computer system, one or more overlapping rules that exist in both the first set of rules and the second set of rules, wherein each rule of the one or more overlapping rules is configured to: (i) process the first parameters to estimate the first value; and (ii) process the second parameters to estimate the second value;
applying, by the computer system, the one or more overlapping rules to the first set of data to estimate the first value;
applying, by the computer system, the one or more overlapping rules to the second set of data to estimate the second value, wherein applying the one or more overlapping rules includes, for each combined identifier:
measuring a velocity metric between at least two consecutive clicks associated with the combined identifier,
determining an elapsed time during which the device associated with the combined identifier interacted with the advertisement; and
assigning values to clicks associated with the combined identifier based at least in part on the velocity metric and the elapsed time;
processing, by the computer system, the first value and the second value to estimate a correction factor;
using, by the computer system, the correction factor to normalize the first value to generate a normalized first value; and
using, by the computer system, the correction factor to normalize the second value to generate a normalized second value so that the first value and the second value are on a same scale.
7 . The system of claim 6 , wherein the first set of data and the second set of data are received from a server log.
8 . The system of claim 6 , wherein assigning a value to the clicks is further based on IP addresses associated with the clicks.
9 . The system of claim 6 , wherein:
the values indicate quality of the clicks; and
higher quality clicks are indicative of network traffic having desirable characteristics.
10 . The system of claim 6 , wherein:
the values indicate quality of the clicks; and
lower quality clicks are indicative of fraudulent, likely fraudulent, or otherwise non-productive network traffic.
11 . A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause one or more data processors of a computer system to perform one or more operations including:
receiving, by a computer system comprising one or more hardware processors, a first set of data that identifies a first plurality of clicks by a first set of devices interacting via a network environment with an advertisement displayed on a publisher website, and a second set of data that identifies a second plurality of clicks by a second set of devices interacting via the network environment with the advertisement displayed on the publisher website, wherein each click of the first plurality of clicks and the second plurality of clicks is associated with a combined identifier that includes: (i) a device identifier of a device of the first set of devices or the second set of devices; and (ii) at least two bytes of an IP address associated with the device identifier;
receiving, by the computer system, a first set of rules that is applied to one or more first parameters associated with the first set of data and a second set of rules that is applied to one or more second parameters associated with the second set of data, wherein:
the first parameters are used to estimate a first value representing characteristics associated with the first plurality of clicks performed by the first set of devices; and
the second parameters are used to estimate a second value representing characteristics associated with the second plurality of clicks performed by the second set of devices;
identifying, by the computer system, one or more overlapping rules that exist in both the first set of rules and the second set of rules, wherein each rule of the one or more overlapping rules is configured to: (i) process the first parameters to estimate the first value; and (ii) process the second parameters to estimate the second value;
applying, by the computer system, the one or more overlapping rules to the first set of data to estimate the first value;
applying, by the computer system, the one or more overlapping rules to the second set of data to estimate the second value, wherein applying the one or more overlapping rules includes, for each combined identifier:
measuring a velocity metric between at least two consecutive clicks associated with the combined identifier,
determining an elapsed time during which the device associated with the combined identifier interacted with the advertisement; and
assigning values to clicks associated with the combined identifier based at least in part on the velocity metric and the elapsed time;
processing, by the computer system, the first value and the second value to estimate a correction factor;
using, by the computer system, the correction factor to normalize the first value to generate a normalized first value; and
using, by the computer system, the correction factor to normalize the second value to generate a normalized second value so that the first value and the second value are on a same scale.
12 . The computer-program product of claim 11 , wherein the first set of data and the second set of data are received from a server log.
13 . The computer-program product of claim 11 , wherein assigning a value to the clicks is further based on IP addresses associated with the clicks.
14 . The computer-program product of claim 11 , wherein:
the values indicate quality of the clicks; and
higher quality clicks are indicative of network traffic having desirable characteristics.
15 . The computer-program product of claim 11 , wherein:
the values indicate quality of the clicks; and
lower quality clicks are indicative of fraudulent, likely fraudulent, or otherwise non-productive network traffic.