Predicting the success of new crypto-tokens: the Pump.fun case

2026-02-16

AI Summary

This study investigates the key determinants of whether newly launched crypto tokens on the Pump.fun platform successfully “graduate” to on-chain markets. Leveraging on-chain data, we develop a conditional probability prediction model that integrates the amount of Solana locked in bonding curves, token launch structures, and user behavioral features—marking the first effort to combine structural and behavioral variables to enhance early-stage predictability. Employing both statistical modeling and machine learning techniques, our model significantly outperforms baseline approaches in forecasting graduation outcomes. The findings offer empirical insights into market dynamics such as speculation, manipulation, and informational efficiency, while also providing a practical tool for early-stage token evaluation.

Technology Category

• Game Theory and Economic Paradigms: Mechanism Design
• Reasoning under Uncertainty: Causality
• Machine Learning: Online Learning & Bandits

Application Category

• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies
• Security and Privacy: Cryptocurrency and smart contracts
• Web Mining and Content Analysis: Models for Web evolution

Abstract

We study the dynamics of token launched on Pump.fun, a Solana-based launchpad platform, to identify the determinants of the token success. Pump.fun employs a bonding curve mechanism to bootstrap initial liquidity possibly leading to graduation to the on-chain market, which can be seen as a token success. We build predictive models of the probability of graduation conditional on the current amount of Solana locked in the bonding curve and a set of explanatory variables that capture structural and behavioral aspects of the launch process. Conditioning the graduation probability on these variables significantly improves its predictive power, providing insights into early-stage market behavior, speculative and manipulative dynamics, and the informational efficiency of bonding-curve-based token launches.

Problem

• crypto-token
• Pump.fun
• bonding curve
• token success
• predictive modeling

Innovation

• bonding curve
• token graduation
• predictive modeling
• crypto-token success
• market dynamics