Off The Pace: F1 Lap Decomposition Analytics

Every F1 lap split into seven physically-grounded components, served by a fully client-side pipeline: FastF1 ingestion, dbt + DuckDB transforms, XGBoost models exported to ONNX, and a React app that runs entirely in the browser.

The Off The Pace home dashboard showing lap decomposition analytics, driver ratings, and strategy projections running entirely client-side.

Off The Pace answers the question lap time alone can’t: when a car is off the pace, exactly why? Every lap is split into seven named, additive components fuel, tyre degradation, track rubber, ambient conditions, constructor pace, dirty air, and driver skill so you can see precisely how much of the gap is the car, the tyres, the conditions, or the driver. Underneath that product is a full data and ML platform: a CI-enforced decomposition, a 60-model dbt warehouse, ONNX models with train/serve parity, and a zero-server browser app.

Are you here to…

Evaluate the work

The sixty-second tour for a reviewer: the eight things to notice, then the skills demonstrated and who built it.

Assess the system

The architecture, the build-time vs request-time split, and how it clears a production data-engineering bar.

Use or run it

Clone the repo and ingest your first race, or launch the live app.

How the pipeline fits together

Raw timing data becomes an interactive chart through four layers, each documented in its own tab:

Data

Where the timing data comes from and how to ingest it yourself.

Transform

The seven-term decomposition: dbt models enforced by a CI contract.

Machine Learning

XGBoost models predicting tyre cliff onset and degradation, exported to ONNX.

App

The browser app every chart and simulator above ships from.

By the numbers

7 seasons

2018–2024 of F1 timing data ingested end to end.

149 races

Every lap decomposed and verified against the additive identity.

72 dbt models

620 tests enforce the pipeline on every build.

5 ML models

XGBoost trained, exported to ONNX, running live in the browser.

30 app features

Interactive visualizations, zero server, sub-10ms queries.

0ms server

DuckDB-Wasm + ONNX Runtime Web run the whole stack client-side.

The stack

Data Pipeline & ML

FastF1

Telemetry & lap timing API

Jolpica

Championship standings & pit API

Python

Ingestion & orchestration

DuckDB

In-process data warehouse

dbt

Transform layer & data tests

XGBoost

Gradient-boosted models

App & Inference

React + Vite

App framework & build tool

DuckDB-Wasm

In-browser SQL analytics

ONNX Runtime Web

In-browser ML inference

Infrastructure

Google Cloud Storage

Gold-mart CDN

Firebase

Static hosting

GitHub Actions

CI: tests, drift gates, deploy

What you can do

Degradation Simulator

Dial in a stint compound, fuel load, and dirty air and watch the trained models project pace loss and cliff risk live.

Ghost Race Standings

Every driver re-ranked in equal machinery a counterfactual championship built from the structural pace model.

Lap Decomposition Waterfall

Any lap, any driver: seven causes stacked into one bar that always closes to zero.

Tyre Cliff Survival

How long each compound lasts before the cliff, by circuit and season.

1. A question

   “Did Mercedes’ pit call or Hamilton’s driving win São Paulo 2021?”

2. A decomposition

   fct_lap_residuals splits every lap of the race into fuel, tyre, rubber, ambient, constructor, dirty-air, and driver-skill components see the case study.

3. A model

   The same physics terms feed the ONNX degradation models that power the live simulator.

4. A chart

   The React app queries the gold Parquet mart with DuckDB-Wasm and renders the answer client-side, in milliseconds.

Key Concepts

The vocabulary used throughout the docs pace delta, clean laps, the tyre cliff.

Quick Start

Clone the repo and ingest your first race in five minutes.

Case Studies

Real race decompositions, starting with Hamilton vs Verstappen at São Paulo 2021.