Author Archives: soccerlogic

About soccerlogic

I am data miner/scientist of twenty four year analysis experience of analysing complex data using machine learning tools. After a long and successful career as a Business Intelligence consultant, I founded Soccerlogic, a company that pioneered the application of advanced analytics to improving performance in football and other sports. Believe that artificial intelligence can be a 'game-changer' in team sports as it has proved to be in many other applications. Therefore passionate about finding ways to applying deep learning methods (AI) to further the analysis of team sports, football in particular.

Mohamed Salah at Roma and Liverpool

The analysis shows that Salah performance has much improved at Liverpool. The number of goals scored – double his tally (31 vs. 15) at Roma with roughly the same number of matches and minutes played – is a strong indicator. But we must account that at Roma he had fewer shots (74 vs. 132) as Dzeko was the main target there.the right side of the goal (Pic. 1), while at Liverpool were more evenly distributed, though the right side remained favourite. Logically, this also the side where most of his shots assists came from. Continue reading

Advertisements
Posted in shot statistics, Soccer analytics, Sports Analytics | Tagged , , , , , , , , , , , , | Leave a comment

Is xG any good at predicting game outcomes?

Introduction One can’t afford to ignore Expected Goals (xG) now that Match of the Day are giving the metric such a huge profile. I’m not a massive fan of xG, but I thought it was worth further investigation and so, … Continue reading

Aside | Posted on | Tagged , , , , , , , , , , , | Leave a comment

Conversion rates (SG) by shot Location

How shot location affects goal conversion (xG) in the MLS Continue reading

Aside | Posted on | Tagged , , , , , | Leave a comment

Shooting stars of the MLS

The easiest and (probably) best way to cluster with respect to a binary variable (goals vs. shots) is to use the algorithm known as classification by decision tree induction (DT) Continue reading

Posted in shot statistics, Soccer analytics, Sports Analytics, Uncategorized | Tagged , , , , , , , | Leave a comment

Can we judge performance accurately without knowing The plan?

Football performance is judged by analysing video and data from a match, or from many matches.  But do video and data provide all the information we need to judge performance accurately?  I don’t think so.  A vital piece of information … Continue reading

Posted in Soccer analytics, Sports Analytics | Tagged , , , | Leave a comment

Possession chains and passing sequences

My method is based on the analysis of the Possession of each team. A Possession is defined as a sequence of events (ball touches) which starts when a team gets the ball and ends when the team loses it to the opposition. The method views a football match as a series of alternate Possession. Continue reading

Posted in Passing sequences, Possession chain analysis, Soccer analytics, Soccer match analysis, Sports Analytics | Leave a comment

Rank and Cluster of teams by Shot Statistics – EPL 2015-16

Thanks to Michael Caley‘s for sharing the data (http://cartilagefreecaptain.sbnation.com/2014/2/12/5404348/english-premier-league-shot-statistics) which allowed this analysis to take place.  Michael’s Glossary of the stats copied from the same blog has been added at the bottom. I have taken taken the data from the … Continue reading

Posted in shot statistics, Soccer analytics, Soccer match analysis, Sports Analytics | Tagged , , , , , , | Leave a comment