About me

Independent sports research lab

Hello, I'mLyra.

Stylised 3D floating head of Lyra

A personal lab exploring how data, modelling and product thinking can make sport more understandable.

Why this lab exists

Competition,
made legible.

Sport compresses uncertainty, incentives and human performance into observable decisions. This lab turns those signals into defensible models, tests how information changes behaviour, and builds analytical products that make complex competition easier to reason about.

What I'm drawn to

Three lenses on how sport works.

Not separate disciplines, but connected ways of understanding the same contest: how value is created, how play unfolds, and how the athlete performs.

01

Value & decisions

I study the incentives, information and market signals behind selection, pricing, strategy and competitive balance.

02

The game in motion

I use event, spatial and visual data to understand patterns of play—from tactical structure to player and team behaviour.

03

The athlete as a system

I’m moving toward sensor and biomechanical intelligence: connecting movement, workload and physical state with performance.

Selected work

Project / 01Forecasting

KPL · Esports

OpenKPL Analytics

A reproducible tournament intelligence system combining audited historical series, leakage-safe team-strength modelling, Elo benchmarks, and Monte Carlo progression forecasts.

PythonEloMonte CarloNext.js
Project / 02Forecasting

AFL · Brownlow Medal

Brownlow Intelligence System

An end-to-end expected-vote system modelling player-match performance, coach recognition, and the Brownlow 3–2–1 match constraint, followed by a frozen post-event audit.

CatBoostRolling OOTModel AuditNext.js
Project / 03Forecasting

NBA · 2026 Draft

NBA Draft Intelligence System

A probabilistic draft board combining multi-source mock consensus, betting markets, team-fit modelling, calibrated uncertainty, and Monte Carlo draft simulation.

PythonMonte CarloData PipelineNext.js
Project / 04Forecasting

FIFA · 2026 World Cup

World Cup Forecasting Engine

A probabilistic football platform trained on 49,000+ international matches, combining Elo, Poisson and Dixon–Coles scoring models with full-tournament simulation.

EloDixon–ColesPoissonSimulation

Research · build · learn in public

Interested in the
same questions?

Let's collaborate