Learning from Multi-User Activity Trails for B2B Ad Targeting

TL;DR

This paper proposes a method to improve B2B ad conversion prediction by leveraging collective online activity trails of relevant organizational users, using distributed activity representations to identify relevant users and activities.

Contribution

It introduces a novel approach to identify relevant organizational users and activities for B2B ad targeting, enhancing prediction accuracy and interpretability.

Findings

Improved conversion prediction AUC by 8.8%.

Provided an interpretable list of relevant activities.

Demonstrated effectiveness on Yahoo Gemini data.

Abstract

Online purchase decisions in organizations can go through a complex journey with multiple agents involved in the decision making process. Depending on the product being purchased, and the organizational structure, the process may involve employees who first conduct market research, and then influence decision makers who place the online purchase order. In such cases, the online activity trail of a single individual in the organization may only provide partial information for predicting purchases (conversions). To refine conversion prediction for business-to-business (B2B) products using online activity trails, we introduce the notion of relevant users in an organization with respect to a given B2B advertiser, and leverage the collective activity trails of such relevant users to predict conversions. In particular, our notion of relevant users is tied to a seed list of relevant activities for a B2B advertiser, and we propose a method using distributed activity representations to build such a seed list. Experiments using data from Yahoo Gemini demonstrate that the proposed methods can improve conversion prediction AUC by 8.8%, and provide an interpretable advertiser specific list of activities useful for B2B ad targeting.