본문 바로가기
  • Home

A Machine Learning–Based Analysis of Short-Term Surges and Listing Premiums for Newly Listed Altcoins on Korean Exchanges Using Offshore Prices and Social Signals

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2026, 31(2), pp.87~96
  • DOI : 10.9708/jksci.2026.31.02.087
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : December 31, 2025
  • Accepted : January 23, 2026
  • Published : February 27, 2026

Eun Hong Park 1 Yeong-In Lee 1 Ha Young Kim 1

1연세대학교

Accredited

ABSTRACT

This study investigates the predictability of post-listing price surges and cross-exchange premiums on the Upbit market. This Study is to demonstrate the empirical validity of an integrated analytical framework that combines offshore market signals with online social signals. By integrating pre-listing Binance data with quantified social sentiment from online communities, we evaluated the ex-ante identification of market anomalies, specifically short-term surges and the formation of the "Kimchi Premium". Empirical results indicate that while the MLP model is superior for detecting price surges, a Logistic Regression model augmented with social factors is most effective for identifying compound events of surges and premiums simultaneously. These findings suggest that combining global price dynamics and investor sentiment, provides a robust basis for screening structural inefficiencies in segmented cryptocurrency markets.

Citation status

* References for papers published after 2024 are currently being built.

This paper was written with support from the National Research Foundation of Korea.