# The value of disruptive runs. Or, why Firmino is such a valuable player for Liverpool

The key problem when scouting football players is knowing how they contribute to their team’s performance. A powerful answer to this question comes from looking at how much a player’s actions increases or decreases the chance of his or her team scoring. This approach works very well for on-the-ball actions. In particular for shots (it is exactly what expected goals measures) but also for passes and defensive actions, such as interceptions and blocked balls.

But…there are 22 players on the pitch at any time, all of them contributing to their team’s performance. It isn’t just the player who has the…

# Evaluating actions in football using machine learning

The Twelve football app evaluates players live during the game. Unlike almost all other ranking that claim to evaluate players, ours is based on a rigorous statistical model of how players increase (and decrease) thier team’s chance of scoring. It is based on The Twelve points system, which is a machine learning algorithm developed by Uppsala professor and soccer-mathematician David Sumpter (that’s me!).

Download the App here. It is free and includes a fun game where you can challenge your friends. You can follow live scores and stats, expected goals, and players rankings for all major leagues and the Euros.

# How analytics makes football more fun

My 18-year-old daughter, Elise, has never been that interested in football. I sent her off to summer camps as a kid to try to get her interested. She played for a half season with a local team. And I took her to a few matches (most notably when she was four she saw Arsenal beat Umeå in the first leg of the Champions League final). But football wasn’t really for her. I share a lot of things with Elise, not least our temperament, but a love for the beautiful game isn’t one of them.

But now I have found the…

What does Timnit Gebru’s firing and the recent papers coming out of Google tell us about the state of research at the world’s biggest AI research department.

The high point for Google’s research in to Artifical Intelligence may well turn out to be the 19th of October 2017. This was the date that David Silver and his co-workers at DeepMind published a report, in the journal Nature, showing how their deep-learning algorithm AlphaGo Zero was a better Go player than not only the best human in the world, but all other Go-playing computers.

What was most remarkable about AlphaGo Zero…

# Stanford researchers find that male over-confidence might be costing the tech industry billions

Anyone working in tech will know the type: the mini-Elon Musk. The young man who thinks that his brilliant idea is going to be the next Uber, Spotify or Tesla. He presents himself with confidence and assurance, but you suspect that, deep down, he has no idea what he is talking about.

There are, of course, women of this type as well. And we certainly shouldn’t (based on a few anecdotes) draw conclusions about men and women as a whole.

That’s where researchers can contribute: to find out whether men are, in general, overly-confident in their own abilities and how…

# Has living through a pandemic made us all better at maths?

hen Boris Johnson addressed the nation to announce new coronavirus restrictions last month, he talked about how the virus would “spread again in an exponential way” and warned us that the “iron laws of geometric progression [shout] at us from the graphs”.

My first reaction, as an applied mathematician, was to smile to myself at his careless use of mathematical ideas. Disease spread is nearly always exponential, it is just another way of saying that the virus multiplies over time. So, it is not the exponential nature of the growth itself that has changed, but the multiplication constant (the R…

# Why algorithms are no better than humans at predicting exam results, goals in football, musical taste or criminal reoffending

It is very likely that at least some of the people who suggested using an algorithm to predict A-level results thought that they were being scientific and rational. They imagined that their algorithm would be neutral, remove bias and do an overall better job than the teachers, who are too close to the students to remain clear-headed.

The irony is that it is exactly this thinking that is unscientific, irrational and biased. Let me explain why, starting with a metric from football called ‘expected goals’. Expected goals are calculated by feeding a lot of data (shot location, whether it was…

# What are the Ten Equations?

Maths is often seen as hard.

Not ‘hard’ as in ‘difficult’ (it can be that too, of course) but ‘hard’ as in delivering hard truths, undeniable facts and fool-proof reasoning.

For me, maths isn’t like that. My 20 years of experience as an applied mathematician — modelling everything from gambling and football to racial segregation and epidemics — has taught me that maths has a softer side.

Maths can be used to think about whether you should give up (or stick with) a romantic relationship. It helps you deal with feelings of insecurity that arise when you compare yourself to…

# Entries for the Liverpool Analytics Challenge

I was totally amazed how many entries their were for the ‘Friends oF Tracking’ Liverpool analytics challenge. The brief was:

1, Use one or more of the tools we have learnt so far (pitch control, speed and acceleration, passing networks, pass maps etc.) to analyse the data.

2, Feel free to combine with other data available from other sources on Liverpool.

3, Produce an output (short report/video) that can be communicated either to a coach, a video analyst or players.

4, Write technical details in a separate appendix.