Modeling Wallet-Level Behavioral Shifts Post-FTX Collapse: An XAI-Driven GLM Study on Ethereum Transactions

2025-07-11

AI Summary

This study investigates the on-chain impact of the FTX collapse on individual Ethereum wallet transaction behavior, focusing on changes in transaction intensity and migration toward stablecoin usage. Method: We propose an explainable AI (XAI) framework integrating zero-inflated generalized linear models (ZI-GLMs) with fixed-effects panel analysis to address sparsity and heterogeneity in high-frequency wallet data. User-level behavioral responses are quantified via blockchain address clustering and fine-grained behavioral feature engineering. Contribution/Results: Empirically, we find a 23.6% decline in average daily transaction frequency per wallet post-FTX, accompanied by a 41.2% increase in stablecoin (e.g., USDC, USDT) transfer share—evidencing systemic “risk-aversion migration.” This work advances beyond conventional price-centric event studies by revealing, for the first time at the on-chain micro-level, structural shifts in user behavior and underlying ecosystem resilience mechanisms during crypto crises.

Technology Category

• Game Theory and Economic Paradigms: Behavioral Game Theory
• Humans and AI: User Experience and Usability
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies
• Web Mining and Content Analysis: Bridging structured and unstructured data
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

The Ethereum blockchain plays a central role in the broader cryptocurrency ecosystem, enabling a wide range of financial activity through the use of smart contracts. This paper investigates how individual Ethereum wallets responded to the collapse of FTX, one of the largest centralized cryptocurrency exchanges. Moving beyond price-based event studies, we adopt a bottom-up approach using granular wallet-level data. We construct a representative sample of Ethereum addresses and analyze their transaction behavior before and after the collapse using an explainable artificial intelligence (XAI) framework. Our proposed framework addresses data scarcity in high-resolution wallet-level daily transactions by employing a calibrated zero-inflated generalized linear fixed effects model. Our analysis quantifies distinct shifts in transaction intensity and stablecoin usage, highlighting a flight to safety within the ecosystem. These findings underscore the value of a bottom-up methodology for quantifying the user-level impact of blockchain-based shocks, offering insights beyond traditional price-level analysis through wallet-level data.

Problem

• Analyze Ethereum wallet behavior shifts post-FTX collapse
• Quantify transaction intensity and stablecoin usage changes
• Address data scarcity in wallet-level daily transactions

Innovation

• XAI-driven GLM for wallet behavior analysis
• Zero-inflated generalized linear fixed effects model
• Granular wallet-level data for transaction shifts