PlayeRank

Abstract

The problem of evaluating the performance of soccer players is attracting the interest of many companies and the scientific community, thanks to the availability of massive data capturing all the events generated during a match (e.g., tackles, passes, shots, etc.). Unfortunately, there is no consolidated and widely accepted metric for measuring performance quality in all of its facets. In this article, we design and implement PlayeRank, a data-driven framework that offers a principled multi-dimensional and role-aware evaluation of the performance of soccer players. We build our framework by deploying a massive dataset of soccer-logs and consisting of millions of match events pertaining to four seasons of 18 prominent soccer competitions. By comparing PlayeRank to known algorithms for performance evaluation in soccer, and by exploiting a dataset of players' evaluations made by professional soccer scouts, we show that PlayeRank significantly outperforms the competitors. We also explore the ratings produced by PlayeRank and discover interesting patterns about the nature of excellent performances and what distinguishes the top players from the others. At the end, we explore some applications of PlayeRank-i.e. searching players and player versatility-showing its flexibility and efficiency, which makes it worth to be used in the design of a scalable platform for soccer analytics. 59:2 L. Pappalardo et al. INTRODUCTIONRankings of soccer players and data-driven evaluations of their performance are becoming more central in the soccer industry [4,14,15,20,32,34,40,46]. On the one hand, many sports companies, websites, and television broadcasters-such as Opta, WhoScored.com, and Sky, as well as the plethora of online platforms for fantasy football and e-sports-widely use soccer statistics to compare the performance of professional players with the purpose of increasing fan engagement via critical analyses, insights, and scoring patterns. On the other hand, coaches and team managers are interested in analytic tools to support tactical analysis and monitor the quality of their players during individual matches or entire seasons [11,27]. Not least, soccer scouts and performance analysts are continuously looking for data-driven tools to improve the retrieval of talented players with desired characteristics, based on evaluation criteria that take into account the complexity and the multi-dimensional nature of soccer performance. While selecting talents on the entire space of soccer players is unfeasible (if not impossible!) for humans, data-driven performance scores help select a small subset of the best players who meet specific constraints (e.g., age, performance features and trends, roles). This allows scouts and performance analysts to analyze a smaller set of players, thus saving considerable time and economic resources while broadening scouting operations and career opportunities of talented players.The problem of data-driven evaluation of player performance is gaining interest in the scientific community, too, thanks to t...

The validity of small-sided games in predicting 11-vs-11 soccer game performance

“…The weights for each indicator were derived from its team-wise correlation with a proxy for ingame offensive and defensive success, namely shots on target and shots on target conceded (i.e., a shot on target by the opposite team, both including goals; cf. Pappalardo et al [49]). Specifically, we assessed the team's performance on the performance indicators in each SSG and 11-vs-11 game, and computed Spearman's rank correlations between the indicators their respective in-game success proxy (see Table 1 and S3 Table).…”

“…The correlation coefficients for each indicator were in the expected direction, meaning that greater performance on the offensive indicators was positively associated with shots on target, while greater performance on the defensive indicators was negatively associated with shots on target conceded (see Table 1). Therefore, we transformed the performance indicators for the players to z-scores within each team, multiplied their score with the correlation coefficient, and summed the scores [49]. Additionally, we added the individual player's shots on target to the offensive performance measure, giving it a weight of 1.…”

Data science: a game changer for science and innovation

“…In [3], we can find the definition of quantitative measures of pressing in defensive phases in soccer. Pappalardo et al [33] outlined the automatic and datadriven evaluation of performance in soccer, a ranking system for soccer teams. Sports data science is attracting much interest and is now leading to the release of a large and public dataset of sports events.…”

In-play forecasting in football using event and positional data

“…Event data provides a detailed and ordered sequence of all the player’s actions during the match, such as passes, shots, or tackles 7 . Although efforts to automatically detect events from video 8 or positional data 9 are undertaken, the most reliable and most widely used approach remains to be manual annotation by expert video analysts, supported by human and computer-based quality control 10 – 12 . Each event is described by the time and location where the action took place on the field as well as the event type.…”