Latest News
MIAS Launches Supercomputer to Predict All 380 NPFL Matches for 2026/27 Season
Made In Africa Sport (MIAS), a sports technology and media company, has unveiled a new supercomputer model designed to analyse and predict all 380 matches of the 2026/27 Nigeria Premier Football League (NPFL) season.
The new system, available at npfl.madeinafricasport.com, uses an extensive database of more than 8,000 historical NPFL matches to generate statistical projections for the upcoming campaign.
The 2026/27 NPFL season kicks off on August 28, with 20 clubs scheduled to compete across 38 matchdays.
For every fixture, the MIAS Supercomputer conducts 100,000 Monte Carlo simulations, resulting in 38 million simulations across the entire league season. The model will also be updated after every matchday, enabling its projections to adjust based on new results and changes in team performance.
Beyond predicting individual match results, the system calculates each club’s probability of finishing in every position on the final league table. It also provides estimates of a team’s chances of winning the title, securing continental qualification or suffering relegation.
The platform combines historical and recent performances with head-to-head records, home and away strength, goalscoring statistics and transfer activity to determine the probability of a home win, draw or away victory.
Recent goalscoring form is assessed through goals scored and conceded, while transfer strength is used to account for changes in squad quality that may not yet be reflected in historical match results.
Speaking on the launch, MIAS Executive Director Enitan Obadina said the project was created to bring a stronger data-driven approach to discussions surrounding the NPFL.
“For a league with as much history as the NPFL, we still do not use enough of the data we have,” Obadina said.
He explained that football discussions around form, match outcomes and title contenders are often heavily influenced by opinion, adding that MIAS wants to provide reliable statistical evidence to support those conversations.
“What we are trying to do is put a proper data layer behind those conversations. We have gone through thousands of historical matches and built a system that can turn that information into something people can actually use to understand the league,” he added.
The model also provides expected goals for each team, as well as attacking, defensive and transfer-strength ratings. Transfer strength is calculated separately using players’ previous-season performances, allowing the system to account for squad changes during the transfer window.
MIAS said the model was developed specifically for the NPFL rather than adapting a generic football prediction system used for European or other international leagues.
Historical figures highlight the importance of home advantage in Nigerian domestic football. Since 2003, away teams have won just 601 of 7,966 NPFL matches, representing only 7.5 per cent of all games played during the period.
According to MIAS, incorporating such league-specific trends is essential to ensuring that the model reflects the realities of Nigerian football.
After calculating probabilities for individual fixtures, the supercomputer simulates the entire season millions of times to produce projected final standings and position-by-position probabilities for every club.
Obadina stressed that the system is not intended to replace football knowledge or human judgement, but rather to provide another tool for analysing the competition.
“We are not saying the computer knows what will happen. Football does not work like that. What it can do is show the probability based on the evidence available to it, and that gives you a much better starting point than simply saying a team will win because it looks stronger on paper,” he said.
He added that transparency was also central to the project, with users able to see the factors contributing to each prediction.
The 2026/27 launch is expected to serve as the foundation for further development, with MIAS planning to continuously improve the model as more NPFL data becomes available.
“This is the first major version of what we want to build. We want to keep improving it as more NPFL data becomes available, so that the model becomes more useful from one season to the next,” Obadina said.
He added that the company’s broader ambition is to establish a dependable data infrastructure for African football that can benefit journalists, clubs, analysts, supporters and other stakeholders.
The complete NPFL 2026/27 projections, including match predictions, expected goals, team ratings and the projected league table, are available on the MIAS Supercomputer at npfl.madeinafricasport.com.
