AT the beginning of the year a team of academics at The University of Salford developed a sports analytic machine that can predict sports results.
The machine was tested against one of the top names in UK football, Mark Lawrenson, and left football fans stunned as it not only forecast scores but also the benefits clubs could receive from certain players.
The Sports Analytic Machine, otherwise known as SAM, was developed by Professor Ian McHale, Professor of Sport Analytics at The University of Salford and Tarak Kharrat.
Speaking about why the machine was developed, Professor Ian McHale said: “As a statistician and sports fan, what could be more fun than predicting football match results?
“There is so much interesting stuff that can be done with the new wave of data that is available on sport.
“Predictions are just the tip of the iceberg and a tool to get to more targeted analysis, like assessing the impact of a player on a team.”
In August SAM predicted that Paul Pogba and Zlatan Ibrahimovic would be worth an extra 10 points for Manchester United.
Following United’s 2-1 win over Crystal Palace on Wednesday night, with both goals and assists coming from the pair, this proves that SAM is more than just a clever idea.
However, as seen with the Premier League campaign last season, football is unpredictable.
Professor McHale said: “The start of the season is a particularly difficult period to make predictions.
“Even though SAM knows which players are on the pitch and how good those players are, it is hard to predict how a player who has moved clubs might perform.
“For example, did Paul Pogba play like the Pogba of Juventus in the first few weeks of the season? Probably not, and it meant that our predictions for Manchester United were a little off – they turned out to be worse than SAM thought!
“How a player will fit in at a new club is hard to take account of in a statistical model and it meant that the prediction for the first few weeks of the season were less successful than they are now.”
The machine takes into account multiple factors to come up with its predictions, such as: recent results, which team is at home, the strength of teams that both sides have played, as well as the quality and the form of the players on the pitch.
The machine can also predict other sports, such as tennis, cricket and golf however Professor McHale says for now they are just sticking to football predictions in the media.
So what are SAM’s predictions for this weekend’s Premier League fixtures?
Professor Ian McHale explained: “Data is the fuel of our system. It is entirely done using numbers, there is nothing subjective about the results that SAM comes up with.
“There are several ways to go about making predictions for the results of a football match.
“In fact, lots of academics and people in the gambling industry have tried. The thing all of the methods have in common is that they look to the past to get an idea of what can be expected in the future.
“For example, if a team is in the habit of scoring lots of goals in recent matches, it is reasonable to think that that team might score more than the average number of goals in the next match.
“Conversely, if a team is having a run of conceding lots of goals, it might be expected to concede more than the average in the upcoming game.
“Of course, more recent matches reveal more relevant information than matches a long time ago, and so that is taken into account.”
— Salford Uni News (@SalfordUniNews) August 19, 2016
Co-creator, Tarak Kharrat added: “There are two additional factors from past results that can be used to signal what the future holds.
“First, it matters where the team has been playing: at home, or away. This effect is known as home advantage, and it is pretty easy to detect and measure.
“In fact, if you do this over several years, it looks like home advantage is such that the home team scores about 1.2 times the number of goals the away teams score.
“Second, it matters which teams the team in question has been playing against. We assign each team an attack strength and a defence strength.
“These strengths are estimated from the data. It is this data that is fed into SAM in order to estimate the team strengths.”