主权项 |
1. A computer implemented method for allocating credit for conversions among advertising touchpoints, the computer implemented method comprising:
storing in a computer, a plurality of touchpoint encounters that represent marketing messages exposed to a plurality of users, wherein each of the touchpoint encounters comprise a plurality of attributes and the attributes comprise a plurality of attribute values; sorting the data for the touchpoint encounters in the computer to separate into converting user data, which comprises touchpoint encounters for users that exhibited a positive response to the marketing message, and non-converting user data that comprises touchpoint encounters for users that exhibited a negative response to the marketing message; retrieving, from storage, the converting user data and the non-converting user data; training, using machine-learning techniques in a computer, the converting user data and the non-converting user data as training data to generate attribute importance data that reflects importance of the attributes, relative to other attributes, to the response of the marketing message; training, using machine-learning techniques in a computer, the converting user data and the non-converting user data as training data to generate attribute value lift data that reflects importance of the attribute values, relative to other attribute values, to the response of the marketing message; and calculating, using a computer, a score for a user that measures propensity of the user to convert by aggregating expressions from touchpoint encounters in accordance with:
User Score=α(the attribute importance data,the attribute value lift data)×λ(T1)+α(the attribute importance data,the attribute value lift data)×λ(T2)+α(the attribute importance data,the attribute value lift data)×λ(T3) wherein, α (the attribute importance data, the attribute value lift data) which represents the attribute importance and the attribute value lift for the touchpoint encounter, is calculated using an attribution algorithm with a plurality of coefficients derived from a curve fitting technique, and λ (T1), λ (T2) and λ (T3) represent forgetting factors calculated by multiplying a constant, λ, by an elapsed time from which the user encountered the touchpoint encounter. |