As Payments Go Social: Predicting Venmo User Engagement and Growth with Dynamic Graph Learning

时间：2025年11月28日10：00

Zoom会议号：822 7261 2177

https://us06web.zoom.us/j/82272612177?pwd=paxMNLWzLB4xakK0Eee18mNdwZ71hs.1

Speaker: Hanyu Zhang

Abstract:

Peer-to-peer payment platforms such as Venmo have profoundly transformed social and financial interactions, generating rich behavioral, relational, and network data. Yet, understanding the dynamics of user engagement and growth dynamics in non-contractual settings remain challenging. This study proposes a unified framework, the Multi-Stream Temporal Graph Neural Network (MuST-GNN), that integrates transactional patterns, linguistic features, and network structure. Designed as a joint-task model, it predicts two behavioral outcomes critical to platform growth: engagement among existing users and the acquisition of new users through first-time interactions. Using comprehensive data from Venmo’s early growth period and evaluated in a live-update setting, the findings are threefold. First, MuST-GNN substantially outperforms both CRM-based and graph-only models, with predictive improvements of over 30% for engagement and nearly 20% for acquisition relative to a baseline that excludes multimodal signals. Second, linguistic signals provide the strongest predictive lift, highlighting the relational and contextual value embedded in transaction notes and emojis. Third, attention analyses show that the model dynamically shifts its reliance on different modalities over time. Network position is more predictive when little behavioral history exists, transaction patterns become more important as user activity grows, and language signals dominate as social ties deepen. This research provides a robust framework for understanding how social connections, financial behaviors, and communication jointly drive consumer engagement and growth on networked platforms.

Introduction of Speaker

Hanyu is a PhD Candidate in Quantitative Marketing at the Goizueta Business School, Emory University.

Hanyu is interested in applying statistics, economics, and computer science to model complex, rich, unstructured relational data, such as graphs, networks, and dyadic interactions, to address contemporary marketing problems.

Her research spans two complementary streams. The first focuses on developing and applying graph-based deep learning and artificial intelligence methods to generate customer insights and value predictions in networked marketing contexts, ranging from online social networks to offline mobility networks. The second seeks to uncover the mechanisms that shape consumer behavior within relational and networked environments. Across both streams, she works with large-scale panel data that capture rich behavioral, relational, and contextual information.