This study aims to classify the race strategies of each team in Formula 1 (F1) using JMP's Latent Class Analysis (LCA). The analysis will utilize publicly available race data from the 2018-2025 seasons, including data from FastF1, OpenF1, Jolpica API, and official FIA race results. Explanatory variables will include average pit stop count, first pit stop lap, average stint length, tire compound, pit stops during safety car periods, position changes, and points earned. LCA will objectively classify team strategies, which have traditionally been described based on experience and impressions, and clarify the characteristics of each latent class. Furthermore, by analyzing the relationship between each class and win rates, podium rates, and annual rankings, the study aims to uncover "strategic patterns that lead to victory." This research proposes a new analytical method in sports data analysis and demonstrates its potential for supporting race strategy decision-making and its application to other fields.
