Time-Weighted Multi-Touch Attribution and Channel Relevance in the Customer Journey to Online Purchase

We address statistical issues in attributing revenue to marketing channels and inferring the importance of individual channels in customer journeys toward an online purchase. We describe the relevant data structures and introduce an example. We suggest an asymmetric bathtub shape as appropriate for...

Full description

Saved in:
Bibliographic Details
Published in:Journal of statistical theory and practice 2015-04, Vol.9 (2), p.227-249
Main Authors: Wooff, David A., Anderson, Jillian M.
Format: Article
Language:English
Subjects:
Clickstream
Digital marketing
E-commerce
Mathematics and Statistics
Metrics
Path to conversion
Probability Theory and Stochastic Processes
Sequential analysis
Statistical Theory and Methods
Statistics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We address statistical issues in attributing revenue to marketing channels and inferring the importance of individual channels in customer journeys toward an online purchase. We describe the relevant data structures and introduce an example. We suggest an asymmetric bathtub shape as appropriate for time-weighted revenue attribution to the customer journey, provide an algorithm, and illustrate the method. We suggest a modification to this method when there is independent information available on the relative values of the channels. To infer channel importance, we employ sequential data analysis ideas and restrict to data which ends in a purchase. We propose metrics for source, intermediary, and destination channels based on two- and three-step transitions in fragments of the customer journey. We comment on the practicalities of formal hypothesis testing. We illustrate the ideas and computations using data from a major UK online retailer. Finally, we compare the revenue attributions suggested by the methods in this article with several common attribution methods.
ISSN:1559-8608
1559-8616
DOI:10.1080/15598608.2013.862753