INFLECT-DGNN: Influencer Prediction with Dynamic Graph Neural Networks

TL;DR

This paper introduces INFLECT-DGNN, a novel dynamic graph neural network approach that combines GNNs and RNNs with profit-driven strategies to improve influencer prediction in evolving customer networks.

Contribution

The paper presents a new profit-driven framework using dynamic GNNs and RNNs, with techniques like synthetic oversampling and rolling-window strategy, tailored for influencer prediction in corporate networks.

Findings

RNNs encoding temporal data improve prediction accuracy.

Profit-driven threshold optimization enhances profit outcomes.

Dynamic network modeling outperforms static approaches.

Abstract

Leveraging network information for predictive modeling has become widespread in many domains. Within the realm of referral and targeted marketing, influencer detection stands out as an area that could greatly benefit from the incorporation of dynamic network representation due to the continuous evolution of customer-brand relationships. In this paper, we present INFLECT-DGNN, a new method for profit-driven INFLuencer prEdiCTion with Dynamic Graph Neural Networks that innovatively combines Graph Neural Networks (GNNs) and Recurrent Neural Networks (RNNs) with weighted loss functions, synthetic minority oversampling adapted to graph data, and a carefully crafted rolling-window strategy. We introduce a novel profit-driven framework that supports decision-making based on model predictions. To test the framework, we use a unique corporate dataset with diverse networks, capturing the customer interactions across three cities with different socioeconomic and demographic characteristics. Our results show how using RNNs to encode temporal attributes alongside GNNs significantly improves predictive performance, while the profit-driven framework determines the optimal classification threshold for profit maximization. We compare the results of different models to demonstrate the importance of capturing network representation, temporal dependencies, and using a profit-driven evaluation. Our research has significant implications for the fields of referral and targeted marketing, expanding the technical use of deep graph learning within corporate environments.