Over a million developers have joined DZone.
{{announcement.body}}
{{announcement.title}}

Using AI to Find the Most Overpaid Athletes

DZone's Guide to

Using AI to Find the Most Overpaid Athletes

A recent study set out to explore whether the most highly paid athletes in the world are worth their enormous salaries. The results... probably won't surprise you.

· AI Zone
Free Resource

Insight for I&O leaders on deploying AIOps platforms to enhance performance monitoring today. Read the Guide.

Moneyball famously highlighted the potential of data to propel sports teams towards success. The story of the Oakland Raiders is one of prodigious use of data and its power to overcome teams with much bigger budgets.

Since then, it's rare for any professional sports team to underestimate the power of data — and to an extent, it's destroyed some of the romance of sport as the head rules the heart. A recent study set out to explore whether it has merit, however, and especially whether the most highly paid football players in the world are worth their enormous salaries.

The researchers analyzed the salaries and performances of 6,082 professional football players using machine learning. Each player was analyzed according to 55 different attributes that were designed to reflect the skillset of the player. These included measurements related to performance (such as scoring and passing accuracy), behavior (such as aggression and vision), and abilities (such as speed, acceleration, and ball control). By combining the scores for each of these, the researchers believe they were able to accurately gauge what each player was worth in terms of salary, and by comparing them with their peers, whether they are worth it or not.

Worth the Wage

The analysis produced some fascinating findings. While it might be expected that Lionel Messi and Cristiano Ronaldo should be the best-paid soccer players in the world, the analysis found David De Gea and Mesut Oezil also very near the top of the tree.

Despite the positioning of Messi at the top of the tree, however, the model believed a "fair" salary for him would be roughly half what he currently earns, thus rendering him the most overpaid soccer player in the world (according to the model). Next in the list of most overpaid players were Angel Di Maria, Robin Van Persie, Ivan Rakitic, and Nicolas Otamendi.

Suffice to say, the model does only look at performances on the pitch and don't take account of the commercial value of a player (the Beckham Effect, we could perhaps call it).

It did, however, reveal a number of players that it believed were significantly underpaid, with Manchester City's new signing Bernardo Silva top of the tree (based upon his salary at Monaco rather than his new one). Next in the list were Harry Kane, Granit Xhaka, Timo Horn, and Paco Alcacer.

What Sets Them Apart

Interestingly, a number of attributes seemed common among those who were either underpaid or overpaid. For instance, underpaid players would often excel in areas such as agility, acceleration, speed, balance, and their ability to track the position of the other players.

Overpaid players, by contrast, only really seemed to exceed their peers in terms of their strength.

There were also some interesting distinctions between the leagues. For instance, vision was highly regarded in Germany, whereas finishing was popular in La Liga and tackling in Italy.

Despite there being some outliers, however, most of the time, there was a strong correlation between salary and skill level. Where inequalities exist, however, the researchers suggest a negative impact on player performance. The authors believe a better approach is to apply an objective quantitative method for determining salary baselines that all players are aware of, thus simplifying negotiations and providing a uniform salary scale.

TrueSight is an AIOps platform, powered by machine learning and analytics, that elevates IT operations to address multi-cloud complexity and the speed of digital transformation.

Topics:
ai ,machine learning ,data analytics

Published at DZone with permission of Adi Gaskell, DZone MVB. See the original article here.

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}