Por Renan Filho · 2026-10-24
**Lead**
The use of advanced data analytics and artificial intelligence in Premier League football has reached a point where manager decisions on player selection are increasingly informed by detailed performance metrics. The current competition between Arsenal’s William Saliba and Aston Villa’s Ezri Konsa for a place in the England national team’s defence is a vivid example of how technology is quantifying attributes that were once judged purely by eye – from pressing efficiency to progressive passing – and is directly influencing line‑up calls.
**Contexto**
Over the past decade, clubs in the United Kingdom have invested heavily in technology to gain a competitive edge. Systems such as Opta’s event‑data feeds, STATSports’ GPS trackers worn during training and matches, and platforms like Hudl’s Wyscout have become standard across the top flight. These tools produce a torrent of data points per player per match – distance covered, sprints, tackles, interceptions, ball recoveries, pass completion under pressure – which are then fed into proprietary models. Coaches and analysts no longer rely solely on subjective opinions; they have objective, real‑time feedback.
In the specific case of centre‑backs, newer metrics such as “defensive actions per 90 minutes above the halfway line” or “pressure regains per 90” are being used to rate their suitability for high‑pressing systems. Konsa, for example, has been praised for his composure in possession and his ability to step into midfield – a trait that Aston Villa’s set‑up demands. Saliba, meanwhile, excels in one‑on‑one duels and aerial contests, with his physical data showing exceptional acceleration over short distances.
Clubs also employ computer‑vision systems that track every player on the pitch, generating heat maps and pass networks that reveal structural contributions. These technologies are no longer the preserve of a few elite clubs; they are now widespread across the Championship and even lower leagues. The Football Association has also integrated such analytics into its coach education programmes, encouraging a more evidence‑based approach at youth level.
**Analise**
Why does this matter? The shift towards data‑driven selection has profound implications for how we understand football performance. It reduces the room for bias and forces managers to justify decisions with tangible evidence. In the Saliba‑Konsa debate, for instance, the raw numbers show that Konsa’s progressive passes per 90 are among the highest for English centre‑backs, while Saliba’s interception rate in the Champions League this season is statistically superior. Such figures become ammunition for pundits and can even affect transfer valuations. Technology, therefore, is not merely a back‑office tool; it is shaping the public narrative.
Furthermore, the trend is accelerating. Machine‑learning models can now predict a player’s injury risk based on training load and match fatigue, helping managers rotate squads more intelligently. Some Premier League sides are experimenting with real‑time AI feedback during matches, giving tactical recommendations through headsets. While still controversial, it points to a future where the line between human judgement and algorithmic insight blurs further.
However, challenges remain. Data quality is not uniform across providers, and different models can give contradictory assessments. There is also the risk of over‑reliance on analytics, neglecting intangible qualities like leadership or adaptability. For players like Saliba and Konsa, the technology can both help and hinder – it highlights their strengths but also exposes any weaknesses to the entire coaching staff.
**Fontes**
This article draws on publicly reported statistics from Opta, STATSports product information, and technical analyses published by The Athletic regarding William Saliba and Ezri Konsa’s performance data. Additional context comes from Football Association coaching guidelines and industry reports on sports technology adoption in English football.