Salvato in:
Dettagli Bibliografici
Autori principali: Falk, Brett Hemenway, Tsoukalas, Gerry, Zhang, Niuniu
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2311.18717
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917941334769664
author Falk, Brett Hemenway
Tsoukalas, Gerry
Zhang, Niuniu
author_facet Falk, Brett Hemenway
Tsoukalas, Gerry
Zhang, Niuniu
contents Existing studies on crypto wash trading often use indirect statistical methods or leaked private data, both with inherent limitations. This paper leverages public on-chain NFT data for a more direct and granular estimation. Analyzing three major exchanges, we find that ~38% (30-40%) of trades and ~60% (25-95%) of traded value likely involve manipulation, with significant variation across exchanges. This direct evidence enables a critical reassessment of existing indirect methods, identifying roundedness-based regressions à la Cong et al. (2023) as most promising, though still error-prone in the NFT setting. To address this, we develop an AI-based estimator that integrates these regressions in a machine learning framework, significantly reducing both exchange- and trade-level estimation errors in NFT markets (and beyond).
format Preprint
id arxiv_https___arxiv_org_abs_2311_18717
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Can AI Detect Wash Trading? Evidence from NFTs
Falk, Brett Hemenway
Tsoukalas, Gerry
Zhang, Niuniu
General Economics
Economics
Cryptography and Security
Multiagent Systems
Trading and Market Microstructure
Applications
Existing studies on crypto wash trading often use indirect statistical methods or leaked private data, both with inherent limitations. This paper leverages public on-chain NFT data for a more direct and granular estimation. Analyzing three major exchanges, we find that ~38% (30-40%) of trades and ~60% (25-95%) of traded value likely involve manipulation, with significant variation across exchanges. This direct evidence enables a critical reassessment of existing indirect methods, identifying roundedness-based regressions à la Cong et al. (2023) as most promising, though still error-prone in the NFT setting. To address this, we develop an AI-based estimator that integrates these regressions in a machine learning framework, significantly reducing both exchange- and trade-level estimation errors in NFT markets (and beyond).
title Can AI Detect Wash Trading? Evidence from NFTs
topic General Economics
Economics
Cryptography and Security
Multiagent Systems
Trading and Market Microstructure
Applications
url https://arxiv.org/abs/2311.18717