PU GNN: Chargeback Fraud Detection in P2E MMORPGs via Graph Attention Networks with Imbalanced PU Labels

TL;DR

This paper introduces PU GNN, a graph attention network-based method with PU loss and GraphSMOTE, to effectively detect chargeback fraud in P2E MMORPGs with imbalanced data, outperforming existing approaches.

Contribution

The paper presents a novel chargeback fraud detection model combining graph attention networks, PU loss, and GraphSMOTE for imbalanced P2E MMORPG datasets, improving detection accuracy.

Findings

PU GNN outperforms existing methods on real-world datasets.

The model effectively handles imbalanced chargeback fraud data.

GraphSMOTE enhances the model's ability to detect minority class instances.

Abstract

The recent advent of play-to-earn (P2E) systems in massively multiplayer online role-playing games (MMORPGs) has made in-game goods interchangeable with real-world values more than ever before. The goods in the P2E MMORPGs can be directly exchanged with cryptocurrencies such as Bitcoin, Ethereum, or Klaytn via blockchain networks. Unlike traditional in-game goods, once they had been written to the blockchains, P2E goods cannot be restored by the game operation teams even with chargeback fraud such as payment fraud, cancellation, or refund. To tackle the problem, we propose a novel chargeback fraud prediction method, PU GNN, which leverages graph attention networks with PU loss to capture both the players' in-game behavior with P2E token transaction patterns. With the adoption of modified GraphSMOTE, the proposed model handles the imbalanced distribution of labels in chargeback fraud datasets. The conducted experiments on three real-world P2E MMORPG datasets demonstrate that PU GNN achieves superior performances over previously suggested methods.