System and Method for Attributing Engagement Score Over a Channel
A scoring probability system for determining the probability of a user to convert an action based upon a single score related to that user. The scoring probability system provides attribution to each channel responsible for leading to a conversion based upon the single score.
1 . A probability scoring system configured to provide attribution for a user converting on a given website, the probability scoring system comprising:
a) a memory; and
b) a processor configured to:
i) receive actions of the user;
ii) parse out the actions to form segment interests of the user;
iii) generate sessions from the actions;
iv) generate a score from the segment interests and the sessions of the user; and
v) determine channel credit for each channel associated with the segment interests and sessions.
2 . The system of claim 1 , wherein the processor is further configured to determine channel credit by determining the score change for each session, determining the total score change for all the sessions, and dividing the score change for each session by the total score change to determine a session credit.
3 . The system of claim 2 , wherein the processor is further configured to generate the channel credit from session credit by identifying the channels utilized in the session and distributing the channel credit from the session credit proportionally.
4 . The system of claim 1 , wherein the sessions further comprise a sequence of exposures, wherein the processor is further configured to identify channels associated with each exposure.
5 . The system of claim 1 , wherein the processor is further configured to utilize the time between sessions to determine the score for the segment interests and the sessions of the user.
6 . The system of claim 1 , wherein the processor is further configured to determine the channel credit based upon channel priority.
7 . The system of claim 1 , wherein the processor is further configured to determine the channel credit based upon exposure type on the channel.
8 . The system of claim 1 , wherein the segments are determined by a lookback window.
9 . The system of claim 1 , wherein the actions comprise events and conversions.
10 . The system of claim 1 , wherein the processor is further configured to generate the score by determining the probability of a conversion with the segment interest.
11 . A method for attributing channel credit to channels leading to a conversion by a user on a website, comprising:
a) generating a score for segment interests and sessions of the user; and
b) determining channel credit for each channel associated with the segment interests and sessions.
12 . The method of claim 11 , wherein the segment interests and sessions of the user are generated by receiving actions of the user, parsing out the actions to form segment interests of the user, and generating generate sessions from the actions.
13 . The method of claim 11 , wherein the sessions further comprise a sequence of exposures, and further comprising identifying the channels associated with each exposure in the sessions.
14 . The method of claim 11 , wherein determining channel credit further comprises determining the score change for each session, determining the total score change for all the sessions, and dividing the score change for each session by the total score change to determine a session credit.
15 . The method of claim 14 , wherein determining the channel credit further comprises identifying the channels utilized in the session and distributing the channel credit from the session credit proportionally.
16 . The method of claim 11 , wherein generating a score for segment interests and sessions further comprises utilizing the time between sessions to determine the score for the segment interests and the sessions of the user.