Systems and Methods for Determining Advertisement Traffic Quality
A method determines advertisement traffic quality. The method receives traffic data for user interactions with a digital advertisement. Rules have quality correlation coefficients and parameters associated with the user interactions to determine if the rules are applicable. The method partitions the traffic data into sessions, where each session is a subset of user interactions by a single user. For each session and each rule, the method uses data from the session as values for the parameters of the rule, thereby determining if the rule is applicable to the session. When applicable to the session, the method generates results according to the traffic data for the session and the quality correlation coefficient for the rule. The method calculates a session score as a summation of the generated results for the rules determined to be applicable to the session, and provides the session scores for the traffic data to a billing platform.
1 . A method of determining advertisement traffic quality, performed at a computing device having one or more processors and memory storing one or more programs configured for execution by the one or more processors, the method comprising:
receiving traffic data for user interactions with a digital advertisement;
selecting a plurality of rules, each rule having a respective quality correlation coefficient and specifying a respective set of one or more parameters associated with the user interactions with the digital advertisement to determine if the respective rule is applicable; and
partitioning the traffic data into one or more sessions, each session corresponding to at least a subset of the user interactions with the digital advertisement by a single respective user;
for each session of the one or more sessions:
for each rule of the plurality of rules:
using data from the respective session as values for the respective parameters of the respective rule, determining if the respective rule is applicable to the respective session;
in accordance with a determination that the respective rule is applicable to the respective session, generating a respective result according to the traffic data for the respective session and the respective quality correlation coefficient for the respective rule; and
calculating a respective session score as a summation of the generated results for the rules determined to be applicable to the respective session; and
providing the session scores for the traffic data to a billing platform.
2 . The method of claim 1 , further comprising:
converting each session score to an ordinal scale so that the session scores for the traffic data are provided on the ordinal scale.
3 . The method of claim 1 , further comprising:
normalizing each session score so that the session scores are provided on a normalized scale.
4 . The method of claim 1 , wherein the traffic data is received from a server log.
5 . The method of claim 1 , wherein each session of the one or more sessions is identified based on a respective device identifier and/or a respective IP address.
6 . The method of claim 1 , further comprising:
receiving supplemental data regarding the traffic data; and
interpreting a first user interaction in a first session based on the supplemental data, wherein the session score for the first session is calculated, based at least in part, on the interpretation of the respective agent interaction.
7 . The method of claim 1 , wherein at least one of the sessions consists of a single click on the digital advertisement.
8 . The method of claim 1 , wherein at least one of the sessions consists of multiple clicks on the digital advertisement.
9 . The method of claim 1 , wherein the traffic data corresponds to a single web page.
10 . The method of claim 1 , wherein the traffic data corresponds to a single website.
11 . The method of claim 10 , further comprising:
calculating an aggregate score for the website, wherein:
the aggregate score is a summation of session scores for sessions in the traffic data for the website; and
the aggregate score is indication of quality of traffic to the website.
12 . The method of claim 11 , wherein the aggregate score is a summation of session scores for all sessions in the traffic data for the website.
13 . The method of claim 11 , wherein the aggregate score is a summation of session scores for a subset, less than all, of sessions in the traffic data for the website.
14 . The method of claim 10 , further comprising:
identifying an environment corresponding to the traffic data, wherein the environment is identified based on the publisher, advertiser, agent, website, and/or digital advertisement, and selecting the plurality of rules includes retrieving a predefined set of rules for the identified environment.
15 . The method of claim 1 , wherein the traffic data corresponds to a plurality of websites.
16 . The method of claim 15 , further comprising aggregating session scores for each of two or more websites of the plurality of websites, thereby determining relative quality of traffic to each of the two or more websites.
17 . The method of claim 1 , wherein providing the session scores for the traffic data to a billing platform includes providing component scores for each session score.
18 . The method of claim 17 , wherein providing the session scores for the traffic data to a billing platform includes providing a respective weight applied to each component score.
19 . The method of claim 17 , wherein at least one session score consists of a single component score.
20 . The method of claim 17 , wherein at least one session score comprises a plurality of component scores.
21 . A computer system, comprising:
one or more processors; and
memory storing one or more programs configured for execution by the one or more processors, the one or more programs comprising instructions for:
receiving traffic data for a digital advertisement;
selecting a plurality of rules, each rule having a respective quality correlation coefficient and specifying a respective set of one or more parameters associated with user interactions with the digital advertisement to determine if the respective rule is applicable; and
partitioning the traffic data into one or more sessions, each session corresponding to at least a subset of user actions with the digital advertisement by a single respective user;
for each session of the one or more sessions:
for each rule of the plurality of rules:
using data from the respective session as values for the respective parameters of the respective rule, determining if the respective rule is applicable to the respective session;
in accordance with a determination that the respective rule is applicable to the respective session, generating a respective result according to the traffic data for the respective session and the respective quality correlation coefficient for the respective rule; and
calculating a respective session score as a summation of the generated results for the rules determined to be applicable to the respective session; and
providing the session scores for the traffic data to a billing platform.
22 . The computer system of claim 21 , wherein the traffic data corresponds to a single website.
23 . The computer system of claim 21 , wherein the one or more programs further comprise instructions for calculating an aggregate score for the website, wherein:
the aggregate score is a summation of session scores for sessions in the traffic data for the website; and
the aggregate score is indication of quality of traffic to the website.
24 . The computer system of claim 21 , wherein the one or more programs further comprise instructions for identifying an environment corresponding to the traffic data based on a type corresponding to the website, wherein selecting the plurality of rules includes retrieving a predefined set of rules for the identified environment.
25 . The computer system of claim 21 , wherein each session of the one or more sessions is identified based on a respective device identifier and/or a respective IP address.