Soccer Match Research Articles

Forecasting extremes of football players’ performance in matches

This study evaluates the use of simple linear or piecewise linear predictive models to predict extreme performance metrics in soccer matches, based on historical training and to match data of soccer players from RKS Raków Częstochowa football club. The data were collected from January to June 2023. The collected training and matched data average is 9000 records per month. A standard workweek at the RKS Academy consisted of 5 training units and at least 1 match. The best individual models found predict selected game performance metrics with a relative error of 2.3%, suggesting an excellent model fit between prediction and the actual value. This is illustrated by input data metric called “Metabolic Time Zone 5 and 6 Per Distance”, and output data by “Decelarations Total Distance in Zone 5 and 6 Per Distance”—calculated for in 3 min sliding window and characterized by the highest value of the generated parameter based on High Metabolic Load Distance (HMLD). The result concerns models run on aggregated performance metrics developed in APEX-PRO system using expert knowledge in soccer training, while raw GPS location-based models performing worse but still acceptably. Although we believe that the accuracy of the models still has limited reliability, their clarity and up-to-date quality make them useful in the daily planning of training activities and the management of workloads that affect player performance in the upcoming match, as well as the tactical decisions of the coach. More accurate predictions are given by individual models compared to aggregated models (player position), but there are exceptions where group models also perform very well. Adding a second metric to the input did not show a significant difference in the analyzed examples (the results are very similar). Our findings indicate that the model based on metrics from the last match also effectively predict extreme motor performances occurring in the game. In the case of the analyzed player, it was at the input “Accelerations Total Time Per Distance in Zone 6” at the output “Distance in Zone 6”. Specific training or match parameters can be key in predicting exceptional soccer performance, but they can also vary depending on the analyzed player. This confirms the need for further analysis of this issue.

Sentiment Analysis for the Identification of Negative Situations in Soccer Matches Using Social Networks and Artificial Intelligence Techniques

Sentiment Analysis for the Identification of Negative Situations in Soccer Matches Using Social Networks and Artificial Intelligence Techniques

Oral but Not Topical Sodium Bicarbonate Improves Repeated Sprint Performance During Simulated Soccer Match Play Exercise in Collegiate Athletes.

This study investigated the effect of oral and topical sodium bicarbonate (SB) on soccer-specific performance during simulated soccer exercise. In a block randomized, double-blind, crossover design, 10 collegiate male soccer players (stature: 181.7 ± 3.2cm, body mass: 81.7 ± 10.5kg) performed soccer-specific performance tests (countermovement jumps, Illinois agility, 8 × 25m repeated sprints) throughout a 90-min soccer-specific aerobic field test (SAFT90) following 0.3g/kg body mass SB in capsules (SB-ORAL), 0.9036g/kg body mass PR Lotion (SB-LOTION), or placebo capsules and lotion (PLA). Soccer-specific performance tests were conducted pre-SAFT90, during half-time and post-SAFT90. Blood samples were analyzed for acid-base balance (pH; bicarbonate, HCO3-) and strong ions (sodium, Na+; potassium, K+). Average sprint times were quicker for SB-ORAL than PLA during half-time (3.7%; p = .049; g = .57) and post-SAFT90 (4.9%; p = .041; g = .66). SB-ORAL increased pH and HCO3- prewarm-up and during half-time (p < .05), and lowered K+ during half-time (p = .035) compared with PLA. SB-LOTION increased pH (p = .019) and lowered K+ (p = .012) during half-time compared with PLA. SB-LOTION increased Na+ postexercise compared with PLA (p = .008). Repeated sprint times during simulated soccer exercise improved for SB-ORAL, which might have been mechanistically underpinned by elevated blood buffering capacity and greater regulation of strong ion concentration. Consuming SB in capsules is a more effective strategy than topical SB application for improving blood buffering capacity and repeated sprint performance throughout competitive soccer matches.

Acute acetaminophen ingestion improves the recovery of neuromuscular fatigue following simulated soccer match-play

ObjectiveThis study aimed to investigate the impact of acute acetaminophen (ACT) ingestion on the responses of neuromuscular function, biomarkers of muscle damage, and physical performance during the 72-h recovery period following simulated soccer match-play. DesignThe study followed a crossover randomized, double-blind, placebo-controlled trial design. MethodsDuring the two experimental sessions, thirteen semi-professional male soccer players completed a 90-min simulated soccer match, 60 min after oral ingestion of 1 g ACT or placebo (PL). Maximal voluntary contraction (MVC) and twitch responses of the knee extensors muscles, elicited through electrical femoral nerve stimulation, were utilized to evaluate both peripheral fatigue (potentiated twitch force, Qtw,pot) and central fatigue (voluntary activation, VA). Performance was assessed through countermovement jump (CMJ) and 20 m sprint tests. Creatine kinase (CK) and lactate dehydrogenase (LDH) were also measured. ResultsSmaller reductions were observed in MVC (−13.3 ± 7.5 % vs. -24.7 ± 11.1 %) and VA (−3.8 ± 4.4 % vs. -12.9 ± 5.4 %) in the ACT compared to the PL condition immediately after simulated soccer match-play (p < 0.05). Afterwards, these parameters were recovered 24 h earlier in the ACT session compared to the PL session. Furthermore, the 20 m sprint performance was significantly better throughout the recovery period in the ACT session compared to the PL session. ConclusionThe findings of this study showed that acute ingestion of 1 g of ACT (1 h before exercise) attenuated the decrease in MVC and VA levels after exercise, as well as improved 20 m sprint performance.

Recovery patterns of low-frequency fatigue in elite youth soccer players after official match

This study aimed to analyze the associations between recovery of low-frequency fatigue, jump height and perceptual responses following official soccer matches. Forty-two male youth elite soccer players (age: 17.13±0.70 years; height: 179.17±5.94 cm; weight: 69.74±4.91 kg) participated in this study. Low-frequency fatigue, countermovement jump, perceived fatigue, muscle soreness and perceived recovery were assessed at -2h, +30 min, +24h and +48h relative to the match. Linear mixed models analysis showed that low-frequency fatigue was reduced at the match-end (ES=-0.679 [95% CI = -1.01; -0.34]; p&lt;.001) but returned to baseline after 24h (ES=0.149 [95% CI = -0.26; 0.56]; p=1.00). Perceptual responses were impaired for up to 48 hours following the match (ES=-0.868–1.174; p&lt;.001). Countermovement jump did not differ between any time point (ES=-0.204–0.216; p&gt;0.05). Additionally, the within-subject correlation analysis showed that low-frequency fatigue pre- to post-match changes presented moderate to large associations with perceived fatigue (rm[57]=-0.43; p&lt;.001), muscle soreness (rm[57]=-0.52; p&lt;.001) and perceived recovery (rm[57]=0.38; p=.003). The assessment of low-frequency fatigue could serve as an additional objective measurement for monitoring post-match fatigue, as findings suggest that young elite soccer players experience transient reductions following match-play, which are strongly correlated with subjective markers of recovery.

Contextualised physical metrics: The physical demands vary with phase of play during elite soccer match play.

The physical demands of elite soccer match play have traditionally been measured using aggregated whole-match metrics. However, match play is increasingly considered as distinct phases of play, although the influence of phase of play on match physical demands remains largely unknown. This study compared physical intensity, acceleration and deceleration demands, between phases of play and according to playing position. The duration of each match from a major European league (n=1083) was divided into one of five reciprocal phases (for the in-/out-of-possession team) using event and tracking data: build-up/high-block, progression/mid-block, chance creation/low-block, fast attack/fast defence, or attacking transition/defensive transition. Player tracking data were used to calculate physical intensity as the rate of distance covered (m⋅min-1) in total and within five speed categories, and the proportion of time spent accelerating and decelerating (>2ms-2) during each phase of play. Rate of distance covered in total differed markedly with phase of play; fast attack 35%-53% greater, and fast defence 33%-50% greater, than other in-/out-of-possession phases respectively, and these effects were amplified for the rate of distance covered at higher speeds (e.g., sprinting ≥4-fold differences between phases). Match phase also affected the proportion of time spent accelerating and decelerating (highest for fast attack and chance creation, respectively), especially when in-possession for forwards and when out-of-possession for defenders (p<0.001). Phase of play had a large effect on the physical intensity of match play, particularly rates of distance covered at higher speeds, as well as the acceleration and deceleration demands, and in a position specific manner.

Predicting soccer matches with complex networks and machine learning

Abstract Soccer attracts the attention of many researchers and professionals in the sports industry. Therefore, the incorporation of science into the sport is constantly growing, with increasing investments in performance analysis and sports prediction industries. This study aims to (i) highlight the use of complex networks as an alternative tool for predicting soccer match outcomes and (ii) show how the combination of structural analysis of passing networks with match statistical data can provide deeper insights into the game patterns and strategies used by teams. In order to do so, complex network metrics and match statistics were used to build machine learning models that predict the wins and losses of soccer teams in different leagues. The results showed that models based on passing networks were as effective as ‘traditional’ models, which use general match statistics. Another finding was that by combining both approaches, more accurate models were obtained than when they were used separately, demonstrating that the fusion of such approaches can offer a deeper understanding of game patterns, allowing the comprehension of tactics employed by teams relationships between players, their positions and interactions during matches. It is worth mentioning that both network metrics and match statistics were important and impactful for the mixed model. Furthermore, the use of networks with a lower granularity of temporal evolution (such as creating a network for each half of the match) performed better than a single network for the entire game.

Hallux Extensus as a Rare Complication of Crural Fracture and Its Surgical Treatment

Hallux extensus is a persistent dorsiflexion of the first metatarsophalangeal joint. Apart from many other causes, it can also be caused by contracture of the extensor hallucis longus muscle, in our case resulting from surgical treatment of crural fracture. The authors present the case of a 17-year-old soccer player who sustained a fracture of both shin and calf bone during a soccer match and underwent surgical treatment with intramedullary nailing. While compartment syndrome wasn't observed, a postoperative complication in the form of progressive development of a dynamic type of hallux extensus was reported. The reason behind this complication was later found to be the interaction of the osteosynthesis material with the extensor hallucis longus muscle, which led to its scarring and shortening. A Z-lengthening of the musculus extensor hallucis longus tendon was indicated and performed with a good clinical outcome. During surgery, an anatomical variation in the course of the extensor hallucis longus was observed, which had to be taken into account to achieve a successful surgical outcome. Key words: cock-up big toe deformity, musculus extensor hallucis longus contracture, Z-lengthening tenotomy, crural fracture complication.

Elite women's soccer match demand can be described using complexity-based analyses and multifractals

The present study aimed to investigate the variability of the displacements in elite women soccer players during official matches according to the position of the players and to the match progression using non-linear analyses (entropy and multifractal spectrum).Sixty-three velocity profiles from global positioning devices of elite professional women soccer players were analyzed. The mean, coefficient of variation, and maximum velocity were calculated during the match using four equal segments. Sample entropy and seven parameters derived from the multifractal detrended fluctuation analysis were also calculated. The players were split into five field playing positions: forwards (FW), offensive midfielders (OM), defensive midfielders (DM), central defenders (CD), and lateral defenders (LD).No significant playing position × period interaction was found for the different parameters analyzed. However, most parameters showed a significant main effect for playing position (p < .01) and period (p < .01). Compared to the other players, FW and OM have the lowest entropy. All players showed a dominance of small velocity fluctuations but FW players showed the widest multifractal spectrum primarily. In contrast, CD had a narrow spectrum and reduced amount of small fluctuations. As the game progressed, mean velocity and entropy significantly decreased. In contrast, the multifractal peak value significantly alongside with changes in asymmetry.From the present results, velocity profiles during elite women's soccer games depicted multifractal features sensitive to player position and match segment, which can help to understand the dynamics and variability of players' responses during a match.

Physical fitness, psychological characteristics, and game performance in youth male soccer players of different levels of competition

ABSTRACT This cross-sectional study examined the differences and associations regarding physical fitness, psychological characteristics, and game performance between elite (n = 64), sub-elite (n = 82), and non-elite (n = 97) youth male soccer players aged 16.2 ± 0.5 years. Physical fitness parameters were assessed using field tests, psychological characteristics were evaluated using validated questionnaires and technical – tactical data were recorded during a competitive soccer match using a multicamera, semiautomatic optical tracking system. Elite players demonstrated superior performance in cardiorespiratory fitness, countermovement jump (CMJ), 10 m sprint, and agility, compared to the sub-elite and the non-elite players. Also, the elite and sub-elite players had faster 40 m sprints than the non-elite players. Game performance was significantly better in the elite group than the other groups and was associated with coping with the adversity and coachability, tension-anxiety, anger-hostility, and fatigue-inertia subscales. Among the physical fitness parameters examined, only agility and CMJ were associated with game performance. In conclusion, elite youth soccer players performed significantly better in various physical fitness and psychological parameters and demonstrated a higher game performance indicator score compared to their sub-elite and non-elite peers. Results suggested that physical fitness and psychological parameters are essential predictors of game performance.

Evaluation of Blood Lactate among Different Player Roles: A Pilot Study on Competitive Young Male Soccer Players.

Soccer match requires anaerobic and aerobic energetic metabolism. The aim of this pilot study was to investigate the changes in blood lactate concentration in young male soccer players in different playing roles at different time points after the soccer match. Following an initial screening of 134 young soccer athletes, 8 male athletes (average age of 15.5 ± 5 SD) were chosen for their characteristics similar to those of competitive athletes. Players were categorized as goalkeeper, central defender, central midfielder, and forward. Blood lactate concentrations were determined using a portable device at different times (10 min, 5 and 16 h) after the soccer match by a maximum effort test on a treadmill. The data were analyzed by one-way analysis of variance ANOVA, followed by Bonferroni's post-hoc test. The following results (mean ± SD) were obtained: VO2max (%) 60.33 ± 3.10; blood lactate (mM) end match (10 min) 2.17 ± 0.78, post-match-early (after 5 h) 2.2 ± 0.42, postmatch-late (16 h) 3.2 ± 0.84. ANOVA analysis indicated that the blood LA concentrations at end-match (10 min) and post-match-early (5 h) were statistically significative lower than those determined at post-match-late (16 h) (p < 0.05). These results suggest that aerobic mechanisms can also use LA as an energy source, contributing to the reduction of its blood concentration. This effect can be due to reduced maximal work during a soccer match and to the LA removal during exercise at reduced intensity. These data can provide indications for planning suitable training strategies for young male soccer players.

Physical and Muscular Performance in a Professional Soccer Player with a Posterior Cruciate Ligament Injury Following an Isokinetic Exercise Program: A Case Report.

The comprehensive treatment for an athlete who sustains a complete posterior cruciate ligament (PCL) injury remains unclear. The purpose of this case report is to describe the effects of an isokinetic exercise program on muscle performance and physical function in a professional soccer player with a PCL injury. Case Report. A 23-year-old male professional soccer player injured his right knee (non-dominant) during a soccer match, with magnetic resonance imaging confirming a complete PCL rupture. The athlete completed 23 sessions of isokinetic treatment over nine weeks to improve physical function and muscle performance. The concentric mode was used to evaluate quadriceps and hamstrings performance isokinetically at angular velocities of 60 °/s, 120 °/s, and 300 °/s. The LEFS questionnaire was used to evaluate physical function. The assessment occurred before starting the treatment and at the end of nine weeks. An athlete with similar anthropometric characteristics was invited to participate and serve as a control, in order to better understand the athlete's assessment results. After nine weeks, peak torque normalized to body mass (PT/BM) improved to 4.0 N.m/kg for knee extensors (control: 3.6 Nm/kg) and 2.3 N.m/kg for knee flexors (control: 1.9 Nm/kg) at 60 °/s. This increase in PT was reflected in the hamstrings-to-quadriceps (H:Q) ratio post-treatment (57 %). At the end of treatment, the athlete returned to sports activities with 98.7 % restored physical function as measured by the LEFS (Score: 79 points). The results demonstrated that the isokinetic treatment improved knee functional capacity, with increased PT/BM for knee extensors and flexors and enhanced torque-holding capacity, indicating improved muscle performance. 5.

Right Leg Spasms And Fasciculations - Slide Tackle During A Soccer Match

Right Leg Spasms And Fasciculations - Slide Tackle During A Soccer Match

Is Travel Associated With Match Performance in Elite North American Professional Soccer? An Exploratory Study.

Travel fatigue impacts cognitive and physiologic systems, but its association with elite soccer match performance is unclear. In this retrospective observational study, we aimed to explore the association between travel and match outcomes in elite North American soccer. Travel data and match outcomes(team points or goals scored and conceded) and physical performance outcomes from 26 elite professional soccer teams and their players were analyzed (148 matches [team-based data] and 1252 player matches from 297 players; age 22.7 [4.5]y). Player- and match-level correlations between performance measures and both acute and cumulated travel metrics were analyzed. Cumulative travel metrics were positively associated with team (travel distance [r = .20; 95% CI, .03-.25], travel time [r = .20; .06-.37], and time away [r = .20; .06-.37]) and individual player (travel distance, [r = .14; .08-.19], travel time [r = .17-.23], and time away [r = .13; .07-.18]) high-intensity running. Cumulative time away was negatively associated with team points (r = -.14; -.28 to -.001) and positively associated with goals conceded (r = .14; .01-.27); no clear association between acute travel metrics and match outcomes or physical performance was observed. As travel cumulated, away teams and their players ran more but for less reward (team points), although the magnitude of these associations was small. These data are exploratory and do not imply acausal relationship; however, further research should consider cumulation of travel.

A data- and knowledge-driven framework for developing machine learning models to predict soccer match outcomes

The 2023 Soccer Prediction Challenge invited the machine learning community to develop innovative methods to predict the outcomes of 736 future soccer matches. The Challenge included two tasks. Task 1 was to forecast the exact match score, i.e., the number of goals scored by each team. Task 2 was to predict the match outcome as probability vector over the three possible result categories: victory of the home team, draw, and victory of the away team. Here, we present a new data- and knowledge-driven framework for building machine learning models from readily available data to predict soccer match outcomes. A key component of this framework is an innovative approach to modeling interdependent time series data of competing entities. Using this framework, we developed various predictive models based on k-nearest neighbors, artificial neural networks, naive Bayes, and ordinal forests, which we applied to the two tasks of the 2023 Soccer Prediction Challenge. Among all submissions to the Challenge, our machine learning models based on k-nearest neighbors and neural networks achieved top performances. Our main insights from the Challenge are that relatively simple learning algorithms perform remarkably well compared to more complex algorithms, and that the key to successful predictions lies in how well soccer domain knowledge can be incorporated in the modeling process.

Variation in Accelerometer-Derived Instantaneous Acceleration Distribution Curves of Elite Male Soccer Players According to Playing Position: A Pilot Study.

The incorporation of triaxial accelerometers into Global Positioning Systems (GPS) has significantly advanced our understanding of accelerations in sports. However, inter-positional differences are unknown. This study aimed to explore the variability of acceleration and deceleration (Acc) distribution curves according to players' positions during soccer matches. Thirty-seven male players from a national-level Portuguese club were monitored using 10 Hz GPS with an embedded accelerometer during the 2021/2022 season. Resultant Acc was obtained from the x (lateral), y (frontal/back), and z (vertical) axes and expressed in gravitational units (g). Statistical Parametric Mapping was employed to compare playing positions: central defenders (CD), fullbacks (FB), central midfielders (CM), wide midfielders (WM), and strikers (ST). All positions exhibited a decreasing Acc distribution curve, very similar in shape, with a high frequency of events in the lower ranges (i.e., 0 to 1 g) and a lower frequency of events in the higher values (2 to 10 g). Post hoc comparisons revealed significant differences between all positions, except between FB and WM. Out of 1000 points in the curve, CD had 540, 535, 414, and 264 different points compared to FB, CM, WM, and ST, respectively. These findings indicate that players in different positions face distinct demands during matches, emphasizing the need for position-specific Acc analysis and training programming. By analyzing Acc as a continuous variable, this study highlights the importance of individualized monitoring to ensure the comprehensive and precise tracking of all player activities, without overlooking or omitting critical information.

Analysis of the impact of different intensities and time periods on the physical and technical performance of professional soccer players

Soccer match simulations provide valuable information on player performance and training methods but how intensity during a game affects a player's physical/technical performance has yet to be explored. The objective of the study was to analyse the impact of variable intensity intervals during the first block of the Copenhagen Soccer Test. A repeated measures study was designed to compare three intensity levels, three time periods and their effects on sprint speed, perceived effort, goal shooting accuracy, dribbling, and long pass accuracy in professional soccer players. The comparison analysis between different phases showed a significant decrease in sprint speed (p &lt; 0.001) and an increase in perceived effort (p &lt; 0.001), however, the technical variables did not change (p &gt; 0.05). When comparing the data based on intensity, significant decreases were observed in all variables (p &lt; 0.001). The combined analysis of the results indicates that the speed decreases and the rate of perceived exertion increases as the simulation progresses. Meanwhile, the accuracy of goal kicks, dribbling, and long passes are negatively affected by high-intensity efforts, but demonstrate recovery over the course of the simulation. The increase in intensity affects the speed more than the accuracy of shots on goal, dribbling and passing. Keywords: Performance, Soccer, Intensity, Physical performance, Technical performance.

The Influence of Playing Position on Physical, Physiological, and Technical Demands in Adult Male Soccer Matches: A Systematic Scoping Review with Evidence Gap Map.

There has been an increase in studies examining the demands of soccer relative to each playing position in recent years. Understanding the physical, physiological, and technical demands on soccer players according to their positional role during competitive matches is necessary to understand match requirements and develop position-specific training practices. Thereby, there is a clear need to synthesize the information on the different profiles of each playing position. This review aimed to organize the literature investigating physical, physiological, and technical demands according to playing positions and provide a framework to identify gaps and suggestions for future studies. A systematic search was conducted in October 2023 using four electronic databases: Web of Science, SPORTDiscus, PubMed and Scopus. The review followed PRISMA 2020 guidelines and the PRISMA-ScR extension for Scoping Reviews. The studies were included if the sample comprised adult male soccer players categorized from Tier 3 to Tier 5 (i.e., highly trained/national level, elite/international level, or world class) and compared the physical, physiological, or technical parameters across playing positions. A total of 178 studies met the inclusion criteria and were included in the review. The number of teams, players, and matches analyzed per study varied considerably. Although a range of classifications were reported across studies, 59% of studies classified players as central defenders, full-backs, central midfielders, wide midfielders, and forwards. The findings suggests that central and external midfielders, and external defenders cover greater total and high-speed distance than forwards or central defenders. Sprint distance was higher in external midfielders versus all other positions. Defenders and central midfielders perform more passes than external midfielders and forwards. Heart rate was the most commonly reported physiological variable across playing positions. When expressed as a percentage of maximal heart rate, midfielders presented higher mean values than all other playing positions. This scoping review demonstrates that there are differences in the demands on players across playing positions in soccer. Training practices in soccer should be based on the specific requirements of each positional role to ensure players can fulfill their tactical responsibilities during the game.

The flag effect on the physical performance of soccer assistant referees

The aim of the study is to compere the performance of the assistant referee without and with the flag, based on existing and novel tests. Introduction: Millions of fans around the world are invested in the game of soccer, cheering on their favorite team, practicing their skills in the park, or simply watching from afar via the media. As such, fairness in refereeing is of the utmost importance, regardless of the level of game or the teams who are playing. The refereeing team plays a critical role in enforcing the rules of the game and ensuring fair play on the field. In addition to working together in the utmost coordination, the referee, two assistant referees, and the standby official are required to oversee the entire match, while making crucial decisions in split seconds. In addition to their verbal communications, assistant referees must carry and use their flag throughout the game, as means for signally their decisions. When running along the sideline, assistant referees hold the flag in opposite hand to the direction in which they’re moving at that time – resulting in up to 30% of their movements during the game being sideways movements. Testing and comparing the athletic abilities of assistant referees is therefore an essential component in ensuring the accuracy and fairness of soccer matches. Assistant referees play a critical role in enforcing the rules of the game, and their ability to run quickly and accurately while holding a flag can have a significant impact on the outcome of the performance. Participants: 18 assistant referees (two female) who are on the staff of the National League in the Israel Soccer Association. The participants’ mean (±SD) variables were as follows: age=29yrs (±3.4); height=178cm (±0.06); weight=68.22kg (±10.45); fat percent=14.67% (±4.86); and seniority on the league=3.11yrs (±1.45). Results: Show that in all the tests the performance was significant better without the flag (RST, agility test and linear speed), the performance decrement % (RST), show no significant result, P&lt;0.05, t (0.91) = 17. Conclusions: the referee run faster without the flags but the no deferent in the fatigue, so they have to train and testing with flags like in the game.

Stochastic Extensions of the Elo Rating System

This work studies how the Elo rating system can be applied to score-based sports, where it is gaining popularity, and in particular for predicting the result at any point of a game, extending its statistical basis to stochastic processes. We derive some new theoretical results for this model and use them to implement Elo ratings for basketball and soccer leagues, where the assumptions of our model are tested and found to be mostly accurate. We showcase several metrics for comparing the performance of different rating systems and determine whether adding a feature has a statistically significant impact. Finally, we propose an Elo model based on a discrete process for the score that allows us to obtain draw probabilities for soccer matches and has a performance competitive with alternatives like SPI ratings.