Catching the Rug: Early Prediction of Fraudulent Memecoins on Solana via Machine Learning

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Jianghai Li, Pavel Kuznetsov, Yury Yanovich, Konstantin Nott-Whaley, Igor Vodolazov
• Venue: arXiv: cs.AI
• Published: 2026-08-20
• Collected: 2026-08-21
• URL: http://arxiv.org/abs/2608.20271v1
• PDF: https://arxiv.org/pdf/2608.20271v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

This research focuses on predicting rug pulls, a form of fraud in memecoins traded on the Solana blockchain, using machine learning models. The study assembles a dataset of over 6 million tokens traded over 7 months and finds that most of these tokens exhibit signs of rug pull within an hour of launch, necessitating short-term prediction. Despite not having access to code-level features, the researchers demonstrate the effectiveness of Gradient Boosting (XGBoost) in predicting potential rug pulls using only the first 5 minutes of trading data. The study also explores cross-platform generalization between two platforms, PumpFun and Raydium, and finds that combining data from multiple sources enhances detection reliability.

What the Document Says

• The study examines rug pulls in memecoins traded on the Solana blockchain.
• A dataset of 6.4 million tokens over 7 months was assembled for analysis.
• Most memecoins exhibit rug pull characteristics within an hour of launch.
• Classic machine learning models, particularly Gradient Boosting (XGBoost), are effective in predicting potential rug pulls using only the first 5 minutes of trading data.
• The study explores cross-platform generalization between PumpFun and Raydium.

Key Concepts Mentioned

• memecoins
• rug pull
• Solana blockchain
• machine learning
• Gradient Boosting (XGBoost)
• liquidity manipulation
• social dynamics

Claims Made by the Document

• A majority of memecoins on Solana exhibit rug pull characteristics within an hour of launch.
• Classic machine learning models, particularly Gradient Boosting (XGBoost), are effective in predicting potential rug pulls using only the first 5 minutes of trading data.

Evidence Used

• Analysis of a dataset of 6.4 million tokens over 7 months

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

The rapid proliferation of memecoins on blockchain platforms has increased the risk of fraudulent activities, particularly rug pulls. While previous studies have focused on Ethereum-based tokens, this paper shifts the spotlight to Solana, the leading blockchain for memecoins by trading volume and token count. Unlike Ethereum, where rug pulls often exploit smart contract backdoors, Solana memecoin rug pulls are predominantly driven by liquidity manipulation and social dynamics. This research pioneers large-scale rug pull early detection in the Solana ecosystem by assembling a dataset of 6.4 million tokens over 7 months. Market analysis reveals that a vast majority of these memecoins exhibit rug pull characteristics within one hour of launch, highlighting the urgency of short-horizon prediction. Despite the absence of code-level features, we demonstrate that classic machine learning models, particularly Gradient Boosting (XGBoost), achieve robust performance in detecting potential rug pulls using only the first 5 minutes of trading data. Furthermore, we evaluate cross-platform generalization between PumpFun and Raydium, revealing that multi-source data fusion significantly mitigates domain shift and improves detection reliability. This study advances the understanding of DeFi fraud on high-throughput chains and provides a practical framework for protecting investors.