Made In Africa Sport (MIAS), a sports tech and media company, has launched a supercomputer powered by artificial intelligence. This system will analyze and predict all 380 matches of the 2026/27 Nigeria Premier Football League (NPFL) season.
The model is available on the MIAS platform. It uses over 8,000 past NPFL matches in its database to make predictions for the new season, which kicked off on 28 August with 20 clubs playing across 38 matchdays.
The company stated that the system runs 100,000 Monte Carlo simulations for each of the 380 fixtures. This means there are 38 million simulations throughout the season.
The predictions will be updated after each matchday to reflect new results and any changes in the performances of the clubs.
The model does more than just predict the winner of each match. It also estimates the probability of every club finishing in each position on the final table. This includes their chances of winning the league, qualifying for continental competitions, or being relegated.
Fans can find the complete 2026/27 NPFL predictions on the MIAS Supercomputer. This includes match outcomes, expected goals, team ratings, and the projected league table.
At the launch, MIAS Executive Director Enitan Obadina said the product was created to fill what he called a gap in analyzing the NPFL.
“For a league with as much history as the NPFL, we still do not use enough of the data we have,” Mr Obadina said.
“Every week, there are talks about which team is in form, who will win a match, or who will challenge for the title. But many of these discussions are based on opinions and guesses.
“What we aim to do is put a proper data layer behind those discussions. We have analyzed thousands of historical matches and built a system that can turn that data into something useful for understanding the league.”
How the Model Works
The model combines data from past performances with head-to-head records, venue strength, goal-scoring, and transfer activity. This helps it predict the chances of a home win, draw, or away victory for each match.
It also looks at previous meetings between teams and their home and away records. Goal-scoring form is measured by how many goals teams have scored and conceded in recent matches. Transfer activity is also considered to account for changes in squad quality that might not be seen in past results.
The final prediction shows the outcome with the highest probability, expected goals, and other factors that influenced the projection.
Mr Obadina emphasized that the system is not meant to replace football knowledge or judgement.
“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. That gives you a much better starting point than just saying a team will win because it looks stronger on paper.
“The key for us is that people can see how a prediction was made. If we say a team has a 60 percent chance of winning, there is data behind that number. The user can see the factors that contributed to it.”
More Than Match Predictions
The MIAS Supercomputer also predicts how many goals each team is expected to score. It provides ratings for attacking, defensive, and transfer strength.
Transfer strength looks at a player’s performance in the previous season. This helps the model factor in changes in squad quality that might not be shown by historical match data, especially given the number of changes made by NPFL clubs during transfer windows.
Home Advantage
MIAS mentioned that the model was built specifically around the NPFL's characteristics. It does not use a generic football prediction model.
Historical data shows the importance of home advantage in the NPFL. Since 2003, away teams have won 601 of the 7,966 NPFL matches recorded. This is only about 7.5 percent of the matches.
The company said this historical pattern helps ensure the predictions reflect the real situation in Nigerian football and not trends from European or other leagues.
Season Projection
After figuring out the probabilities for each fixture, the system simulates the whole NPFL season. It uses these results to create a projected final league table.
These projections will change throughout the season as actual results are added to the model.
Mr Obadina said that the 2026/27 edition is the first major version of a larger data project that MIAS wants to develop over time.
“This is the first major version of what we want to create. We want to keep improving it as more NPFL data comes in. This will make the model more useful from one season to the next.
“Our bigger goal is to build a reliable data structure around African football. We want journalists, clubs, analysts, supporters, and others to ask meaningful questions about our leagues and get credible data to work with,” he concluded.
Drop your comment
No comments yet — be the first to drop the gist 👇