The question
How do driver performance metrics, weather conditions, and pit-stop times affect the probability of winning a Formula 1 race? The team studied historical Formula 1 results and enriched race data to understand the factors associated with finishing performance.
Research & modeling
Cleaned and integrated driver, constructor, race, qualifying, pit-stop, and weather data to explore relationships with race outcomes.
Investigated a linear regression approach for estimating finishing position using race and performance features.
Trained a Random Forest classifier to predict categories of grid-to-finish position improvement from driver points, constructor points, starting grid position, circuit, pit stops, and wet-race status.
Selected result
The notebook identifies driver championship points, starting grid position, constructor points, and circuit information as influential model features. These are associations in the explored data, not proof of causal effects.
What I took away
Race strategy is a multi-variable problem: driver form, team resources, track context, and the starting grid all interact. Modeling race outcomes means considering both sporting intuition and data limitations.
Explore the original work
Read the project notebook ↗Watch the project video ↗Explore the work
Read the original project materials behind this case study.
Fashion & Home Product Tagging