A Time To Event Framework For Multi-touch Attribution

TL;DR

This paper introduces a flexible, real-time multi-touch attribution framework using a Poisson process model for user conversions and an iterative credit assignment algorithm, addressing the need for handling incomplete data and time-varying ad effects.

Contribution

It presents a novel MTA system that models conversions as an inhomogeneous Poisson process and employs an iterative attribution algorithm suitable for dynamic, incomplete data environments.

Findings

Effective handling of continuously updated data

Captures time-varying ad effects

Suitable for real-time budget and bidding decisions

Abstract

Multi-touch attribution (MTA) estimates the relative contributions of the multiple ads a user may see prior to any observed conversions. Increasingly, advertisers also want to base budget and bidding decisions on these attributions, spending more on ads that drive more conversions. We describe two requirements for an MTA system to be suitable for this application: First, it must be able to handle continuously updated and incomplete data. Second, it must be sufficiently flexible to capture that an ad's effect will change over time. We describe an MTA system, consisting of a model for user conversion behavior and a credit assignment algorithm, that satisfies these requirements. Our model for user conversion behavior treats conversions as occurrences in an inhomogeneous Poisson process, while our attribution algorithm is based on iteratively removing the last ad in the path.