Researchers have developed MELT, a new dataset designed to detect high-risk memecoin launches by analyzing behavioral traces on the Solana blockchain. The dataset includes over 41,000 memecoin launches and 200 million transactions, parsed into distinct behavioral records like swaps and wash trades. MELT reveals that coordinated accounts often hold a significant portion of token supply, a strategy that can mislead investors. By extracting 122 behavioral features and risk annotations, MELT enables machine learning models to identify risky launches, which has been shown to reduce investment losses. AI
Summary written by gemini-2.5-flash-lite from 1 sources. How we write summaries →
IMPACT Provides a new dataset and features for ML models to mitigate financial losses from risky memecoin launches.
RANK_REASON The cluster contains an academic paper detailing a new dataset and methodology for detecting high-risk memecoin launches. [lever_c_demoted from research: ic=1 ai=1.0]