Deep Reputation Scoring in DeFi: zScore-Based Wallet Ranking from Liquidity and Trading Signals

2025-07-27

AI Summary

Accurately distinguishing Uniswap users as liquidity providers (LPs) or traders is critical for DeFi risk modeling and on-chain reputation systems. To address this, we propose a dual-dimensional behavioral scoring framework: first, a rule-based blueprint quantifying transaction frequency, holding duration, TVL share, and fee-tier adherence; second, a U-Net–inspired deep residual network that jointly models pool-level contextual features and role-specific behavioral signals for fine-grained classification. Notably, our approach introduces dense skip connections—previously unexplored in on-chain behavior identification—to preserve hierarchical temporal and structural patterns. Evaluated on Uniswap v3 data, it achieves a 12.7% F1-score improvement over baselines. The framework enables scalable, interpretable, and auditable on-chain reputation construction, supporting robust LP-trader differentiation without relying on wallet-label ground truth.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

As decentralized finance (DeFi) evolves, distinguishing between user behaviors - liquidity provision versus active trading - has become vital for risk modeling and on-chain reputation. We propose a behavioral scoring framework for Uniswap that assigns two complementary scores: a Liquidity Provision Score that assesses strategic liquidity contributions, and a Swap Behavior Score that reflects trading intent, volatility exposure, and discipline. The scores are constructed using rule-based blueprints that decompose behavior into volume, frequency, holding time, and withdrawal patterns. To handle edge cases and learn feature interactions, we introduce a deep residual neural network with densely connected skip blocks inspired by the U-Net architecture. We also incorporate pool-level context such as total value locked (TVL), fee tiers, and pool size, allowing the system to differentiate similar user behaviors across pools with varying characteristics. Our framework enables context-aware and scalable DeFi user scoring, supporting improved risk assessment and incentive design. Experiments on Uniswap v3 data show its usefulness for user segmentation and protocol-aligned reputation systems. Although we refer to our metric as zScore, it is independently developed and methodologically different from the cross-protocol system proposed by Udupi et al. Our focus is on role-specific behavioral modeling within Uniswap using blueprint logic and supervised learning.

Problem

• Distinguish liquidity provision vs trading in DeFi risk modeling
• Develop behavioral scoring for Uniswap users using deep learning
• Improve risk assessment and reputation systems in DeFi

Innovation

• Behavioral scoring with liquidity and swap metrics
• Deep residual neural network with U-Net skip blocks
• Pool-level context integration for user differentiation