top of page

Your certificate is now private

CertificateBackground.png

Certificate of Completion

ErdosHorizontal.png

THIS ACKNOWLEDGES THAT

HAS COMPLETED THE SUMMER 2026 DATA SCIENCE BOOT CAMP

Taylor Daniels

Roman Holowinsky, PhD

July 20, 2026

DIRECTOR

DATE

clear.png

TEAM

Balancing Random Pokémon Battles

Greg Knapp, Marz Newman, Mohammed Mannan, Xiaoyu Huang, Taylor Daniels

clear.png

If you had to build two teams of 6 Pokémon to battle, how do you give both teams a fair chance? With over 1,000 Pokémon to choose from, each with different types, abilities, move-sets, and stats, the number of possible teams is astronomical. What if you had to do this randomly? This is exactly the issue that the developers of Pokémon Showdown (“Showdown”) grapple with in curating their most popular game format: the Gen-9 Random Battle.

Ideally, random teams should be balanced so that both players have even chances of winning at match start. Our work in this project tries to analyze just how "well-balanced" (at least, roughly!) these random teams are, by seeing if we can predict a battle’s winner just using the matchup data at battle start.

Screen Shot 2022-06-03 at 11.31.35 AM.png
github URL

©2017-2026 by The Erdős Institute.

bottom of page