CAMTA: Causal Attention Model for Multi-touch Attribution

TL;DR

CAMTA introduces a causal, deep recurrent neural network for multi-touch attribution in digital advertising, improving prediction accuracy and enabling better budget allocation by accounting for user behavior and reducing bias.

Contribution

It presents CAMTA, a novel causal attention-based RNN architecture for personalized multi-touch attribution that minimizes bias and leverages user pre-conversion actions.

Findings

CAMTA outperforms baselines in prediction accuracy on Criteo dataset.

CAMTA provides effective budget allocation insights.

The model accurately captures user behavior in attribution.

Abstract

Advertising channels have evolved from conventional print media, billboards and radio advertising to online digital advertising (ad), where the users are exposed to a sequence of ad campaigns via social networks, display ads, search etc. While advertisers revisit the design of ad campaigns to concurrently serve the requirements emerging out of new ad channels, it is also critical for advertisers to estimate the contribution from touch-points (view, clicks, converts) on different channels, based on the sequence of customer actions. This process of contribution measurement is often referred to as multi-touch attribution (MTA). In this work, we propose CAMTA, a novel deep recurrent neural network architecture which is a casual attribution mechanism for user-personalised MTA in the context of observational data. CAMTA minimizes the selection bias in channel assignment across time-steps and touchpoints. Furthermore, it utilizes the users' pre-conversion actions in a principled way in order to predict pre-channel attribution. To quantitatively benchmark the proposed MTA model, we employ the real world Criteo dataset and demonstrate the superior performance of CAMTA with respect to prediction accuracy as compared to several baselines. In addition, we provide results for budget allocation and user-behaviour modelling on the predicted channel attribution.