ApexRace AI

• 

  Dashboard

Inspiration

Formula 1 races are often decided by small strategy decisions, such as tire choice, pit-stop timing, and driver consistency. Final race results show who finished where, but they do not clearly explain why a driver gained or lost performance during the race. I wanted to build a dashboard that makes F1 strategy easier to understand using real race data.

What it does

ApexRace AI is an interactive Formula 1 analytics dashboard that analyzes lap-by-lap race data and explains whether a driver's performance was affected by tire degradation, pit-stop timing, or race pace consistency. Users can select an F1 season, race, driver, and comparison driver. The dashboard then shows clean race pace trends, tire degradation analysis, pit-stop strategy, driver comparison, and a strategy scorecard. It also provides a race insight summary that explains the key findings in simple language.

How we built it

I built ApexRace AI using Python, Streamlit, FastF1, Pandas, NumPy, and Plotly. FastF1 is used to load real Formula 1 race data. Pandas and NumPy are used for cleaning and analyzing lap data. Plotly is used to create interactive charts. Streamlit is used to build and deploy the web dashboard. The app removes pit laps and unusual slow laps to create a cleaner race pace view. It calculates consistency scores, tire degradation risk, pit timing ratings, and an overall strategy score.

Challenges we ran into

One challenge was making the raw F1 lap data easier to understand. Race data can include pit-in laps, pit-out laps, safety car laps, traffic effects, and outlier laps, so the dashboard needed cleaning logic before showing race pace trends. Another challenge was designing the dashboard so it looked professional and easy to use. I improved the layout with a dark F1-style interface, animated cards, and clearer chart sections.

Accomplishments that we're proud of

I am proud that ApexRace AI is a working live dashboard using real Formula 1 data. It does not only show charts; it also gives strategy insights, tire risk, pit timing analysis, driver comparison, and a final strategy score. I am also proud of building a project that connects sports analytics, data science, and dashboard design into one complete product.

What we learned

I learned how to work with real motorsport data, clean noisy lap-time data, and turn raw race information into useful strategy insights. I also learned how to build a more polished Streamlit dashboard with custom styling and deploy it as a live web app.

What's next for ApexRace AI

Next, I would like to add machine learning lap-time prediction, weather impact analysis, safety car strategy detection, undercut and overcut analysis, team-level strategy comparison, and PDF race report export.

Built With

• analytics
• cloud
• dashboard
• data
• fastf1
• formula
• github
• learning
• machine
• numpy
• pandas
• plotly
• python
• scikit-learn
• sports
• streamlit
• visualization