Predicting Tetris Performance Using Early Keystrokes

Fdg '23: Proceedings of the 18Th International Conference on the Foundations of Digital Games 46:1-4 (2023)
  Copy   BIBTEX

Abstract

In this study, we predict the different levels of performance in a Nintendo Entertainment System (NES) Tetris session based on the score and the number of matches played by the players. Using the first 45 seconds of gameplay, a Random Forest Classifier was trained on the five keys used in the game obtaining a ROC_AUC score of 0.80. Further analysis revealed that the number of down keys (forced drop) and the number of left keys (left translation) are the most relevant keys in this task, showing that by merely including the data from these two keys our Random Forest Classifier reached a ROC_AUC score of 0.83.We conclude that the keylogger data during the early phases of a game session can be successfully used to predict performance in longer sessions of Tetris.

Author Profiles

Analytics

Added to PP
2023-04-13

Downloads
212 (#74,625)

6 months
113 (#42,747)

Historical graph of downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.
How can I increase my downloads?