Bagley College of Engineering Publications and Scholarship

ORCID

Robert Dilworth: https://orcid.org/0009-0005-5497-9810

Abstract

This manuscript presents a comprehensive exploration of optimizing Pokémon gameplay through data-driven methodologies, aimed at enhancing competitive performance in high-stakes environments. In the first section, we introduce a robust Pokémon teambuilding algorithm that leverages statistical analysis of championship-winning compositions. By employing multiple linear regression techniques, we predict team performance based on critical factors such as Base Stat Totals (BSTs) and various coverage types. This integration of data science principles into Pokémon strategy underscores the importance of offensive capabilities over defensive considerations, ultimately contributing to advancements in teambuilding strategies. Our proficiency in R programming facilitated the development of an efficient codebase for data analysis, model fitting, and visualization, showcasing our commitment to statistical computing excellence. Transitioning to the second section, we delve into the intricacies of high-performing Pokémon team compositions within the Scarlet and Violet competitive scene. We investigate pivotal aspects such as item choices, ability influences, and move set dynamics across various tournament circuits. By identifying distinct archetypes based on stat combinations, we evaluate Pokémon’s competitive roles and develop a predictive modeling framework that establishes benchmarks for assessing viability. Our analysis reveals a significant correlation between a Pokémon’s BST and its engagement frequency in Video Game Championship (VGC) tournaments, highlighting the critical role of individual statistics in determining competitive relevance. Through the compilation and examination of VGC tournament data, we uncover a positive trend linking BST with participation frequency, particularly for Regular Pokémon. Collectively, this work not only enhances our understanding of Pokémon strategies but also sets a foundation for future research in competitive gameplay optimization.

DOI

https://doi.org/10.54718/CUBG5659

Publication Date

Fall 11-8-2024

College

James Worth Bagley College of Engineering

Department

Department of Computer Science and Engineering

Keywords

Pokémon, Data Science, Machine Learning, Competitive Gameplay, Statistical Analysis, Predictive Modeling, Video Game Championship (VGC), Team Building, Meta-Analysis, Base Stat Total (BST)

Disciplines

Computer Sciences | Data Science | Theory and Algorithms

Download

Share

COinS