Adobe Global Community

Pages Tagged with ''

Attribution Theory: The Two Best Models for Algorithmic Marketing Attribution – Implemented in Apache Spark and R

In my last post, I illustrated methods for implementing rules-based multi-touch attribution models (such as first touch, last touch, linear, half-life time decay, and U-shaped) using Adobe Analytics Data Feeds, Apache Spark, and R. These models are indeed useful and appealing for analyzing the contribution any marketing channel has to overall conversions. However, they all share a common problem: they’re heuristic – meaning at the end of the day, a human being is still left guessing at marketing performance without any real data to back those guesses.