Skip to main content

Korea University

Organization3 reports

3 reports, presentations and talks by Korea University in the Game Industry Library, the newest “Tracer: A Forensic Framework for Detecting Fraudulent Speedruns from Game Replays” (2025).

Documents

Cover of Tracer: A Forensic Framework for Detecting Fraudulent Speedruns from Game Replays
Whitepaper16 pages

Tracer: A Forensic Framework for Detecting Fraudulent Speedruns from Game Replays

The Tracer framework establishes a rigorous forensic methodology for verifying the authenticity of speedruns, addressing the systemic vulnerabilities inherent in traditional trust-based moderation.

  • The Tracer framework provides a structured, modular approach to detecting speedrun fraud by analyzing audiovisual, physical, and cyberspace artifacts, addressing the current reliance on inconsistent, informal community moderation.
  • Speedrun manipulation techniques have evolved beyond simple video splicing to include complex methods like runtime code injection, macro-based input simulation, and the manipulation of pseudorandom number generator (PRNG) outcomes.
  • High-profile fraud cases, such as the 2020 Minecraft speedrun controversy involving statistically improbable item drop rates, demonstrate that reverse-analyzing game seeds and internal probabilities is a critical forensic tool for verifying authenticity.
Korea UniversitySep 2025
Cover of Action2Score: An Embedding Approach to Score Player Action
Whitepaper20 pages

Action2Score: An Embedding Approach to Score Player Action

Action2Score introduces a sophisticated deep learning embedding model designed to quantify individual player contributions within Multiplayer Online Battle Arena (MOBA) games.

  • The Action2Score model achieves over 99% discernment accuracy in evaluating individual player contributions by analyzing action sequences rather than binary match outcomes.
  • The system utilizes a GRU-SLP architecture trained on a dataset of 245,575 League of Legends matches to map player behavior into a 30-dimensional embedding space.
  • By decoupling performance from final match results, the model effectively identifies the value of support roles that are typically undervalued by traditional metrics like KDA and gold.
Korea UniversityOct 2022
Cover of Oldie Is Goodie: Effective User Retention by In-game Promotion Event Analysis
Whitepaper6 pages

Oldie Is Goodie: Effective User Retention by In-game Promotion Event Analysis

This analysis examines the efficacy of in-game promotional events in mitigating user churn within the Massively Multiplayer Online Role-Playing Game (MMORPG) genre.

  • In-game promotional events for the MMORPG AION increased active user counts by 18% and cumulative users by 19% during a two-week period in early 2016.
  • Promotional events are more effective at preventing churn among existing players than at acquiring new users, with the highest impact observed among mid-level players and those active during daytime hours.
  • While promotional events increased the number of unique buyers by 150%, the total frequency of individual purchase transactions dropped by 10%, indicating a shift away from high-frequency spending.
Korea UniversityOct 2019

Do you work at Korea University? Get a free report of how these documents are read and cited here.