FIFA World Cup 2026Prediction Challenge
Five student teams independently modelled the entire 2026 FIFA World Cup — each building their own data model to predict group stage qualifiers, knockout results, and the eventual champion.
5Teams
22Students
5Rounds
Jun–Jul2026
5 Teams
Each team independently developed their own prediction methodology — no shared models, no collaboration between teams.
01
Architects
ML — Logistic Regression, Random Forest & Gradient Boosting
02
Rovers
Research-driven qualifier selection
03
Elite 4
Power BI — Interactive KPI dashboard & visual analytics
04
Data Wizards
ML — ELO ratings, win rates & full tournament simulation
05
Thunderbolts
ML — Random Forest & full tournament simulation
Leaderboard
| # | Team | R32 | R16 | QF | SF | Final | Total |
|---|---|---|---|---|---|---|---|
| 1 |  Data WizardsML — ELO ratings, win rates & full tournament simulation | 54 | — | — | — | — | 54 |
| 2 |  ArchitectsML — Logistic Regression, Random Forest & Gradient Boosting | 50 | — | — | — | — | 50 |
| 3 |  RoversResearch-driven qualifier selection | 50 | — | — | — | — | 50 |
| 4 |  Elite 4Power BI — Interactive KPI dashboard & visual analytics | 48 | — | — | — | — | 48 |
| 5 |  ThunderboltsML — Random Forest & full tournament simulation | 46 | — | — | — | — | 46 |
Each correct prediction earns 2 points. The team with the most points wins.
Maximum points a team can earn: 124 (R32: 64 · R16: 32 · QF: 16 · SF: 8 · Final: 4)
Tournament Rounds
Click an active round to see all team predictions side by side.
›
›
›
›
Football is called the beautiful game for a reason—it's unpredictable, emotional, and no model or algorithm can accurately predict every result. This FIFA World Cup 2026 Prediction Challenge is not an attempt to claim certainty or guarantee outcomes.
This challenge is a hands-on learning initiative by IntellentX Learning Hub (ITX) to demonstrate how our students transform classroom knowledge into practical application. Five student teams are competing to predict the FIFA World Cup winner using different analytical approaches, machine learning models, statistical techniques, and data-driven assumptions.
Throughout the challenge, students in our Data Science and Data Analytics programmes learn within their own teams by collaborating on research, modelling, and decision-making, while also learning across the classroom by observing, comparing, and discussing the strengths and limitations of each team's methodology. This collaborative environment mirrors how modern data and AI teams operate in the workplace.
The objective is not simply to predict the winner, but to demonstrate ITX's Learn. Build. Launch. approach—where students develop technical skills through engagement, teamwork, critical thinking, experimentation, and real-world datasets.
Win or lose, every prediction provides an opportunity to validate assumptions, learn from outcomes, and improve future models. Because at ITX, the real victory is the learning journey—not predicting the final score.