Statistical Models for Predicting Results

in Professional League of Legends

Robbie Jadowski1 and Stuart Cunningham1,2(B)

1
Department of Computing and Mathematics, Manchester Metropolitan University,
Manchester M1 5GD, UK
[email protected], [email protected]
2
Centre for Advanced Computational Science, Manchester Metropolitan University,
Manchester M1 5GD, UK

Abstract. The esports industry has seen enormous growth in popular-

ity. With increased viewership and revenue, further investment has been
made to improve professional players’ competitive strength. The modern
esports team is a hierarchical business fuelled by investors and sponsor-
ship. This paper is focused on the professional competitions in League of
Legends esports. In existing real-world sports such as football or baseball,
there is great attention paid to statistic driven analysis of the competi-
tion, and these stats are used to quantify player and team performance.
These statistics hold significant value for competitive improvement, the
gambling industry, and market influence within the esports industry.
This paper presents an analysis of data and metrics gathered from pro-
fessional games during 2020 in several League of Legends international
competitions. The objective was to build a predictive model through the
combination of existing data analysis and machine learning that can rate
team and player performance. The best performing model was able to
correctly predict 67% of 306 games. Results indicate that while it is pos-
sible to predict the outcome of a competitive League of Legends game, to
do so with a higher degree of accuracy would require substantially more
data and contextual information.

Keywords: Esports · League of Legends · Machine learning ·

Regression

1 Introduction
Statistical analysis of sports, or sports analytics, has become an increasingly
popular method for recruitment and strategising in modern sport and competi-
tion. The popularisation of sports analytics is often attributed to Billy Beane,
who famously achieved great success as the general manager of the Oakland
Athletics baseball team using a data-driven approach to evaluate and recruit
players on a much lower budget than competing teams. Other teams took note
of this approach and went on to achieve success through data-based decision
c ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2022
Published by Springer Nature Switzerland AG 2022. All Rights Reserved
M. Wölfel et al. (Eds.): ArtsIT 2021, LNICST 422, pp. 138–152, 2022.
https://doi.org/10.1007/978-3-030-95531-1_10
 Statistical Models for Predicting Results in Professional League of Legends 139

making. This success was noticed by executives and owners of teams in other
professional sports leagues, to the point where practically all modern sporting
organisations now recruit analytic experts or entire departments dedicated to
sports analytics [12].
The convenient nature of statistics allows managers and coaches to identify
a player’s strengths and weaknesses at a glance, without having to spectate each
game the players compete in. The same data can used by gambling organisations
to determine probability and assign odds to certain outcomes.
For example, football statistics have evolved to include automated sensing
technology that can track player position, movement and other observations
from fixed and mobile cameras and sensors. Several professional statistical anal-
ysis firms offer data and analysis to professional teams as a product, providing
context to the data collected and helping teams make tactical decisions [2].
Since League of Legends (LoL) is a video game, an abundance of statistics
can be gathered automatically as they are tracked by the game itself. The wealth
of data available provides many opportunities to perform analytics on the game.
Most of the existing forms of public analytics involving LoL is used by jour-
nalists and fans to make comparisons and fuel narratives. Other organisations
provide LoL teams with a paid product package to enhance in-house analysis
and supplement coaching.
The aim of this research is to build a statistical model using metrics from this
data that can accurately rate team and player performance, with the intention
of predicting the outcome of games featuring those players and teams in future
games.

2 League of Legends

League of Legends was released in October 2009, and in the years since its release,
it has developed a competitive infrastructure across multiple regions that rivals
that of traditional sports [8]. Each region’s competitive league features franchised
teams that compete against each other in weekly broadcasts that regularly draw
thousands of viewers and annual inter-regional championships that have drawn
44 million peak concurrent viewers during grand finals [21]. The events feature
grand finals in venues such as the Staples Center, selling out the venue within
1 h of tickets being available [22], and the Beijing National Stadium, catering to
live audiences in their thousands.
LoL is a team-based strategy game where two competing teams of 5 players
aim to destroy their opponents base, canonically named the Nexus. Each game
of League of Legends takes place on the same map, known as Summoner’s Rift.
Summoner’s Rift is split into three lanes, commonly known as Top, middle and
Bottom. These lanes form a path that leads from one team’s base to the other.
The two sides of Summoner’s Rift, referred to as ‘Blue Side’ and ‘Red Side’
are separated by a River that runs from top lane to bottom lane, and the area
in-between the lanes is known collectively as the Jungle. Blue team’s base and
nexus is situated in the bottom-left of the map, while red team’s base and nexus
is in the top-right. A representation of the map is shown in Fig. 1.
140 R. Jadowski and S. Cunningham

Fig. 1. Simplified version of the Summoner’s Rift Map. Original PNG version by
Raizin, SVG rework by sameboat licensed under CC BY-SA 3.0 [17] (Color figure
online)

Players select one of over 140 champions to control in order to complete

the objective and each possesses abilities that aid in combat, navigating the
environment or supporting their team. Each player fulfils a different role for the
team, much like the different positions in a football team. The roles featured
in LoL are: Top Laner; Jungler; Mid Laner; Bot Laner; and Support. Each
corresponds to the area or lane of the map that the player will operate in the
opening of a game, with the Support player often partnering with the Bot Laner.
These roles traditionally feature a typical character archetype, though there are
exceptions and champions that buck the trend.
For a team to reach and destroy the enemy team’s nexus, they must overcome
a series of AI controlled structures known as Turrets. These structures are very
difficult to destroy without assistance, which is usually provided by the waves of
AI controlled minions that spawn periodically from a team’s base. These minions
will follow a lane’s path to the enemy base until they run into the opposing team’s
champions, minions or turrets. Players must aid their minions in their advance in
order to take down Turrets and reach the opposing teams base, while defending
their own Turrets from the opponents.
The map also features neutral objectives, Dragon, Rift Herald and Baron
Nashor. These neutral monsters can be defeated by a team to obtain permanent
and temporary bonuses, ranging from additional movement speed, a percent-
age increase in ability power, or buffs to friendly minions to aid in sieging the
opponents base.
Due to the asymmetrical nature of the map, granting the blue team eas-
ier access to the area that Baron Nashor spawns, combined with the pre-game
champion draft where blue side can choose their first champion before the red
 Statistical Models for Predicting Results in Professional League of Legends 141

team, there is a debate that blue side has an inherent advantage compared to the
red team. Similar to the home advantage often seen in traditional sports. This
advantage will be explored when analysing the data from competitive games and
considered when making predictions if such an advantage exists.

3 Background
The use of player rankings in LoL is recognised as being an important feature of
the game for individuals as well as to ensure the competitive edge of the game
[11], which may arguably extend to system of team rankings and statistics. Previ-
ous work has examined the effect that the ability of LoL players working together
in teams, and the presence of female gender players, has in being able to predict
the competitive performance of those teams, however this relies upon individual
measures being taken from players, such as measures of collective intelligence,
gender, and so forth, that are not intrinsic to the LoL game statistics and so
require additional information gather to take place [10]. Unsurprisingly, much
existing research tends to point towards the influence that individual players,
and their ability to form effective teams, can have on game outcomes [4,5]. How-
ever, in terms of win prediction, it has been shown that for other Multi-player
Online Battle Arena games in professional contexts, accuracy rates of up to 85%
are possible [9].

4 Dataset and Preparation

4.1 Dataset Source
This report is focused on seven competitive leagues in LoL: the LEC (Europe);
LCS (North America); LCS Academy (North America); LCK (South Korea);
PCS (Southeast Asia); CBLOL (Brazil); and TCL (Turkey). While the Chinese
league is the largest and perhaps most dominant region, there is insufficient data
for each individual game available, and so it is excluded from the analysis. By
using the data from every competitive game played during the 2020 spring split
from 24th January 2020 to 2nd March 2020, we aim to predict the outcome
of games that take place in the 2020 summer split. Each training dataset was
validated using 10-fold cross validation. There were a total of 306 games in the
2020 Summer Split dataset used for testing.
There are several independent analysts who create content and collect data of
competitive LoL to enable community-driven analysis and discussion. The data
used in this report was obtained from an independent analyst, Tim Sevenhuysen,
who runs the website oracleselixir.com [19].
The training data featured 882 games of data. Each game includes 12 rows.
One row for each player (10 players) and one row for each team (two teams). In
order to make the data usable it was separated data, into two subsets: the raw
data of per game averages of each team (Table 1); and the raw data of per game
averages of each player. Player statistics comprise of: Position; Games Played;
142 R. Jadowski and S. Cunningham

Win Percentage; Counter-Pick Rate; Total Kills; Total Deaths; Total Assists;
Total Kill/Death/Assist Ratio; Kill Participation; Kill Share; Average Share
of Team’s Deaths; First Blood Rate; Average Gold Difference at 10 min; Aver-
age Experience Difference at 10 min; Average Creep Score Difference at 10 min;
Average Monsters + Minions killed per minute; Average Share of Team’s Total
Creep Score post-15-minutes; Average Damage to Champions per minute; Dam-
age Share; Average Earned Gold per minute; Gold Share; Average Wards Placed
per minute; and Average Wards Cleared per minute. The players are separated by
their role in the team, since different metrics can be more important to specific
roles.

Table 1. Metrics and opposite metrics in the team statistics subset

Metric Opposite
Kills Deaths
Gold at 15 Opponent Gold at 15
XP at 15 Opponent XP at 15
CS at 15 Opponent CS at 15
Towers Opponent Towers
Dragons Opponent Dragons
Vision Score per Minute Opponent Vision Score per Minute
Kills per Minute Opponent Kills per Minute
Damage per Minute Opponent Damage per Minute
Barons Opponent Barons
Heralds Opponent Heralds
Inhibitors Opponent Inhibitors
Wins Losses

4.2 Performance Measures

Pythagorean Expectation. Pythagorean Expectation (PE) is used to calcu-

late the expected total wins for a competitor over a number of games. George
William ‘Bill’ James, known for his approach to analysing professional baseball
using data and statistics, developed the formula to predict a baseball team’s
win percentage from the observed number of runs scored and runs allowed dur-
ing a given baseball season. James is widely recognised for coining the term
Sabermetrics. This term is a combination of the acronym SABR (Society for
American Baseball Research) and the word metrics. Sabermetrics has become
widely accepted as a useful baseball evaluation tool [3]. It is argued that the PE
was the impetus for baseball’s Sabermetricians movement, where, most notably,
the Oakland Athletics adopted statistical principles that revolutionised their
approach to baseball team management [12].
 Statistical Models for Predicting Results in Professional League of Legends 143

S2 1
W = = (1)
S 2 + A2 1 + (A/S)2
In the original formula, W is the win percentage, S is the observed number
of runs scored, and A is the observed number of runs allowed. James initially
used an exponent of 2, inspiring the use of Pythagorean in the formula’s name.
The formula has since been studied to identify the optimal exponent value for
accurate predictions. Different exponents can be calculated for each team in
order to more accurately predict win percentages, and methods to find those
exponents, such as the Pythagenpat formula, have been developed
S + A 0.287
n= (2)
G
where n is the exponent, and G is the total number of games. Though orig-
inally used for baseball, the simple concept of an offensive and defensive stat
forming the foundation of the PE formula means that it can be applied to other
sports [13,15].
For LoL there are several metrics that can be used in an application of PE.
The most obvious one would be kills and deaths. While the win condition of LoL
is not having a higher margin of kills than the other team, it is an obvious met-
ric that usually indicates the more dominant team. Another alternative would
be turrets destroyed vs turrets lost. The planned model for rating teams will
be calculating an overall offensive and defensive rating for each team, so these
ratings can also serve as the values used in the PE formula.

Log5. Once the values of the PE formula for each team are known, we can
use another formula to estimate the probability of one team beating another.
James also devised Log5, a formula that uses two teams’ winning percentages to
calculate head-to-head match up probabilities [14].
pA − pA × pB
pA, B = (3)
pA + pB − 2 × pA × pB
The Log5 formula considers the winning percentage of team A (pA) and team
B (pB) and returns the percentage chance that team A beats team B. From
which we can easily calculate the chance that team B beats team A. We can
experiment using this formula with the values obtained from PE and compare
them to predictions from logistic regression models to see if it offers better or
worse performance.

Strength of Schedule. If two teams have an equal record in sports, it can be

challenging to determine which one could technically be considered the better
team. One way of determining this is to assess the strength of the schedule for
each team. Strength of Schedule (SOS) refers to the strength of the opponents
a team has faced, compared to others [6].
Calculation of SOS involves comparing the combined winning percentages of
each team’s opponents against their own record or adjusting statistics by adding
144 R. Jadowski and S. Cunningham

or subtracting based on an opponent’s record. Assessing a team’s strength of

schedule can lead to interesting insights, where a bad team who appear strong
on paper, may have only played against weaker teams, and a good team with
worse statistics may have only played against stronger teams. Since the LoL
teams that place higher in the rankings during the spring split round robin
phase progress to the spring split playoffs, they end up playing more games
against tougher opponents than other teams. A team’s per game average stats
might be lower than a worse team, simply because they had to play more games
against stronger teams.
This work will be taking SOS into account when analysing the data set, since
many teams in LoL do not play against each other the same amount of times
over the course of a split. This results in a method of adjusting a team’s stats
based on the strength of their opponents, with the goal of identifying a team’s
strength of schedule and building a more accurate representation of a team’s
overall strength.
To calculate a team’s adjusted total, the metric M for a team T is
N

AdjT otalM T = (OppStati − AvgStatM − SideAdvM T ) (4)
i=1

where N is the number of games featuring the selected team, OppStati is the
opponent’s opposite raw stat in row i, AvgStatM is the overall league average
stat for metric M , and SideAdvM T is the average advantage/disadvantage for
metric M on team T ’s side of the map.
The adjustment to the chosen metric is made by dividing AdjT otal by the
number of games a team has played and subtracting that from RawStat
AdjT otalM T
AdjustedStatM T = RawStatM T − (5)
T otalGamesT
where RawStatM T is the raw per-game average stat for metric M for team
T and T otalGamesT is the total amount of games played by team T .
Using this information, one can calculate what a team’s adjusted stats would
be for each metric and compare them to their actual performance. If a team’s
adjusted stats are lower than their actual performance, this would indicate that
the level of their opponents was worse in that metric and vice versa.

5 Evaluation

5.1 Team Ratings

Side Advantage. Before devising and evaluating a model, it is important to
determine if the dataset is balanced or not. In this case, whether the side of
the map a team starts on provides any advantage. While most physical sports
feature a home advantage due to familiar locations, less travel and playing in
front of their own fans, LoL takes place in a virtual environment. Therefore, no
significant difference or advantage for either team should be discovered. Despite
 Statistical Models for Predicting Results in Professional League of Legends 145

this, there are major differences between starting on either side of the map that
could provide an advantage to a team.
It may be argued that the blue side of the map holds an inherent advantage
due to several factors. These include the asymmetrical geometry of Summoner’s
Rift and the isometric point-of-view favouring the blue side of the map. Most
importantly, the pick/ban phase strategy of a team is often dictated by the side of
the map the team is going to playing. Data suggests that this side advantage does
exist. In 2017, professional League of Legends games saw a period where blue
side had a win rate of 64%. So much so that the developers of LoL, have sought to
balance this advantage through various balance updates, such as making dragons
a more lucrative objective.
The dataset used in this study includes 882 games, of which blue side won
477. This equates to a 54.08% win rate for blue side. A chi-square test suggests
that the side of the map does have an impact on a team’s chances of winning
χ2 (1, 882) = 5.878, p = 0.015. This infers that blue wins are expected to be more
prevalent in the dataset, causing a slight imbalance.

Metric Selection. Using all available metrics in a prediction model can be

detrimental to its performance and prediction accuracy. Using a point-biserial
correlation coefficient (PBCC) [23] calculation for each metric, identified which
metrics strongly correlate with the result of a game. Two sets of calculations
were carried out on each metric, one for the true stats of each game, and one
for the per game averages of each team in each game. The tables were split into
calculations for blue side and red side and ordered by the highest averages PBCC
(converted to absolute value).
We selected the top 8 metrics from the red and blue teams because all 8 met-
rics scored above 0.5 absolute true PBCC and 0.25 absolute averages PBCC.

Table 2. Offensive metrics for forming team rating

Metric True PBCC Abs. (Blue/Red) Average PBCC Abs. (Blue/Red)

Towers 0.887/0.891 0.319/0.309
Inhibitors 0.734/0.755 0.293/0.277
Kills 0.644/0.731 0.258/0.267
KPM 0.664/0.735 0.263/0.273

Table 3. Defensive metrics for forming team rating

Metric True PBCC Abs. Average PBCC Abs.

(Blue/Red) (Blue/Red)
Opponent Towers 0.891/0.887 0.316/0.323
Opponent Inhibitors 0.755/0.734 0.285/0.290
Opponent Dragons 0.672/0.636 0.255/0.290
Opponent Barons 0.674/0.574 0.274/0.280
146 R. Jadowski and S. Cunningham

They can also be evenly split into offensive (shown in Table 2) and defensive
(Table 3) metrics, which will form the basis of offensive and defensive team rat-
ings. The coefficient values can be used to calculate a weighting for each metric
when producing a team rating. Another prediction model can also be formed by
using these metrics as features, meaning that the results can be compared to the
prediction models using all available metrics.

Table 4. Weightings for offensive and defensive metrics

Metric Tactic Weight

Kills Offensive 23.24%
KPM Offensive 23.75%
Towers Offensive 27.78%
Inhibitors Offensive 25.23%
Opponent Barons Defensive 24.75%
Opponent Dragons Defensive 22.98%
Opponent Towers Defensive 27.51%
Opponent Inhibitors Defensive 24.77%

Normalization and Team Ratings. In forming team ratings, Z-score nor-

malization was selected over min-max as Z-score does a better job at handling
outliers and will grant a team a higher value if they are drastically better in a
particular metric, rather than pushing all other teams to be within a smaller
range of each other.
Following normalization, the next step was to determine the weight of each
metric. Weighting was calculated using the PBCCs used earlier to select the most
relevant features. The weights were separated into offensive and defensive and
calculated by summing the mean coefficients for each metric for both blue and
red team and then calculating the percentage each mean coefficient contributes,
shown in Table 4.
After calculating the weights, an offensive and defensive rating were formed
using the sum of each normalized metric multiplied by its weight. This creates
two new metrics, the offensive rating and the defensive rating. Figure 2 displays
each team in terms of their offensive and defensive ratings, creating a visual-
ization of where a team’s strengths lie in their play style. These metrics can be
considered opposites, lending themselves to being used in a Pythagorean expec-
tation formula.

Pythagorean Expectation: Exponent. To determine the most accurate PE

exponent for the offensive and defensive ratings, we iteratively evaluated expo-
nents between 0 and 10 and calculated the Mean Absolute Error (MAE) from
each team’s predicted y and actual x win percentages.
 Statistical Models for Predicting Results in Professional League of Legends 147

Fig. 2. Offensive and defensive ratings for all teams.

n
i=1|yi − xi |
M AE = (6)
n
This is done with the intention of finding the PE exponent value that min-
imises the MAE. The values of the defensive rating were inverted and each added
to a constant of 5, since the formula relies on a lower, positive value, defensive
stat being a reflection of a team’s ability. We found a value of 1.82 the most
accurate single exponent to use for this dataset, with MAE of 0.0397. The MAE
values for this exponent range are shown in Fig. 3.

5.2 Player Ratings

Focusing on the performance of an entire team to predict results can be flawed

for several reasons. In competitive LoL, teams may use substitute players to take
the place of another player in a certain role. There is also the case of players
transferring to a different team between each split. Teams will try to sign new
players to replace under-performing ones, or more successful teams might attract
the best players from lesser teams. While some teams tend to maintain a certain
level of dominance despite changing their roster, this is usually down to the
team’s infrastructure and coaching. Most teams will notice a certain change in
performance even by changing just one member of their roster.
148 R. Jadowski and S. Cunningham

Fig. 3. Pythagorean expectation: exponent value calculation.

Predicting future results only by a team’s combined results could lead to

problems if that team changes its roster. In this case, rating each player may
result in more accurate predictions. By assigning each player their own rating,
a modular overall team rating can be formed. The process for creating player
ratings is similar to the process of creating team ratings described in the previous
sub-section.
Rather than choosing the same metrics for every player type in LoL, there
is reason to consider the difference in each class a player can assume, and what
aspects of the game are important for that role. For selection of player met-
rics, the same process was followed as for team metrics, namely selecting the
strongest correlation coefficients and weighting them accordingly. These are dis-
played in Table 5, noting the acronyms: Average Dominance Factor (Dom F);
average Damage dealt to champions Per Minute (DPM); average Gold Difference
between a player and their opponent in their respective role at the 10-min mark
(GD10); average Kills, Deaths and Assists ratio (KDA); average Creep Score
Difference between a player and their opponent in their respective role at the
10-min mark (CSD10); and average experience points (XP) Difference between a
player and their opponent in their respective role at the 10-min mark (XPD10).
After selecting the metrics for each role, the next task was to arrive at an
overall rating. The player statistics dataset is not suitable for an offensive and
defensive metric split, so each player will only have one rating based on the
stated metrics. After calculating each player’s rating, another model can be set
up using each team’s individual player ratings as a feature. Therefore, if a player
is swapped out for a different one in a game, the rating will adjust to match the
new player, affecting prediction outcome.

5.3 Performance Evaluation

Summary of Approaches. A total of seven sets of features and approaches
were evaluated to identify the one resulting in the best prediction outcomes.
These approaches were: (1) the un-adjusted per game metrics per team (UT);
(2) the adjusted per game metrics per teams (AT); (3) the eight weighted metrics
 Statistical Models for Predicting Results in Professional League of Legends 149

Table 5. Player metrics and weightings

Metric PBCC Weight

Top Laner
Win% 0.330 41.32%
Dom F 0.234 29.36%
Assists 0.234 29.33%
Jungle
Win% 0.339 32.04%
Dom F 0.284 26.86%
GD10 0.161 15.20%
XPD10 0.148 14.02%
CSD10 0.126 11.88%
Mid Laner
Win% 0.335 37.12%
Dom F 0.270 29.95%
DPM 0.149 16.49%
GD10 0.148 16.44%
Bot Laner
Win% 0.344 29.36%
KDA 0.266 22.71%
Kills 0.232 19.82%
DPM 0.175 14.89%
GD10 0.155 13.21%
Support
Win% 0.345 29.25%
Dom F 0.263 22.32%
Assists 0.238 20.20%
GD10 0.170 14.43%
XPD10 0.163 13.81%

selected by their PBCC scores per team (WT); (4) the calculated offensive rating
and defensive rating per team (OD); (5) a player rating for each player in both
teams (PR); (6) actual win rate percentages of each team (WP); and (7) the
expected win percentage calculated using the Pythagorean expectation formula
for both teams (PE). Approaches 1 to 5 made use of logistic regression to predict
game outcomes and 6 to 7 made use of the Log5 formula for prediction.

Performance Metrics and Results. The following metrics were used to mea-
sure performance of the approaches: Classification Accuracy (CA) [18]; F1 Score
150 R. Jadowski and S. Cunningham

(F1) [1]; Area Under the Curve (AUC) [7]; Mathews Correlation Coefficient
(MCC) [1]; Log Loss (LL) [18].
Following training of the logistic regression models and calculation of the
Log5 outcomes, the results were obtained for each approach using the test data
set from the 2020 Summer Split, as shown in Table 6, where the highest per-
forming outcome for each metric is highlighted in bold.

Table 6. Evaluation results (Summer 2020)

Model CA F1 (Blue) F1 (Red) AUC MCC LogLoss

UT 0.618 0.670 0.545 0.649 0.217 0.544
AT 0.621 0.669 0.557 0.657 0.226 0.528
WT 0.631 0.685 0.553 0.654 0.242 0.489
OD 0.634 0.689 0.556 0.639 0.248 0.516
PR 0.673 0.724 0.600 0.666 0.329 0.413
WR 0.592 0.654 0.512 0.621 0.168 0.509
PE 0.637 0.691 0.561 0.638 0.255 0.491

The Player Rating model scores best in each performance metric, especially
MCC, while all models suffered lower F1 scores for predicting Red Wins than
predicting Blue Wins. This indicates that the models have more difficulty iden-
tifying if the red team wins, and seems resistant to predict this, despite having
taken the blue side advantage into account during stat adjustments for the mod-
els. Prediction performance of wins for the Player Rating model is illustrated in
Fig. 4.

Fig. 4. Player rating model prediction results.

 Statistical Models for Predicting Results in Professional League of Legends 151

6 Conclusions and Future Work

The Player Rating approach achieved a significant classification accuracy of
67.3% classification when predicting 306 games from the 2020 Summer Split,
which is significantly better than chance χ2 (1, 306) = 11.560, p < 0.001. Com-
pare this to results in the 2015/2016 English Football Premier league season
through logistic regression, where 69.5% accuracy was achieved [16] after iterat-
ing on earlier work that achieved accuracy of 51.06% predicting the 2011/2012
season [20]. As this result is a first iteration, it stands to reason that improve-
ments are possible. The findings may also have utility in player scouting, where
a player may be performing better than their competitors, but is on a worse
performing team.
The Win Rate approach scored worst in all metrics other than LogLoss.
This confirms assumptions can’t be made based on the previous results of teams
alone, but further investigation into their actual performance in other game
metrics reveals that they will better influence future results.
Since the approaches used per game averages rather than game by game
data, they were unlikely to achieve a 90%+ classification accuracy, due to the
inevitability of upsets. Even during the closing periods of a LoL game, the out-
come can be highly volatile due to the nature of the game.
Future work should include a way to update a model after each game is
played and weight more recent games higher than older when calculating a
team’s strength, eventually forgetting those games as they become irrelevant.
For additional experimentation, a combination of team ratings and player rat-
ings would likely be ideal. Due to the small team size in LoL, a roster change
can have massive implications on the future performance of a team. There is
also precedent for dominant teams falling, even without roster changes.

References
1. Chicco, D., Jurman, G.: The advantages of the Matthews correlation coefficient
(MCC) over F1 score and accuracy in binary classification evaluation. BMC
Genomics 21(1), 1–13 (2020)
2. Cintia, P., Giannotti, F., Pappalardo, L., Pedreschi, D., Malvaldi, M.: The harsh
rule of the goals: data-driven performance indicators for football teams. In: 2015
IEEE International Conference on Data Science and Advanced Analytics (DSAA),
pp. 1–10. IEEE (2015)
3. Costa, G.B., Huber, M.R., Saccoman, J.T.: Understanding Sabermetrics: An Intro-
duction to the Science of Baseball Statistics. McFarland, Jefferson (2019)
4. Costa, L.M., Souza, A.C.C., Souza, F.C.M.: An approach for team composition in
league of legends using genetic algorithm. In: 2019 18th Brazilian Symposium on
Computer Games and Digital Entertainment (SBGames), pp. 52–61. IEEE (2019)
5. Do, T.D., Dylan, S.Y., Anwer, S., Wang, S.I.: Using collaborative filtering to rec-
ommend champions in league of legends. In: 2020 IEEE Conference on Games
(CoG), pp. 650–653. IEEE (2020)
6. Fearnhead, P., Taylor, B.M.: Calculating strength of schedule, and choosing teams
for March Madness. Am. Stat. 64(2), 108–115 (2010)
152 R. Jadowski and S. Cunningham

7. Fogarty, J., Baker, R.S., Hudson, S.E.: Case studies in the use of ROC curve
analysis for sensor-based estimates in human computer interaction. In: Proceedings
of Graphics Interface 2005, pp. 129–136 (2005)
8. Games, R.: League of Legends. Riot Games, Garena, Santa Monica, CA, USA
(2009)
9. Hodge, V.J., Devlin, S.M., Sephton, N.J., Block, F.O., Cowling, P.I., Drachen, A.:
Win prediction in multi-player esports: live professional match prediction. IEEE
Trans. Games 13, 368–379 (2019)
10. Kim, Y.J., Engel, D., Woolley, A.W., Lin, J.Y.T., McArthur, N., Malone, T.W.:
What makes a strong team? Using collective intelligence to predict team perfor-
mance in league of legends. In: Proceedings of the 2017 ACM Conference on Com-
puter Supported Cooperative Work and Social Computing, pp. 2316–2329 (2017)
11. Kou, Y., Gui, X., Kow, Y.M.: Ranking practices and distinction in league of leg-
ends. In: Proceedings of the 2016 Annual Symposium on Computer-Human Inter-
action in Play, pp. 4–9 (2016)
12. Lewis, M.: Moneyball: The Art of Winning an Unfair Game. WW Norton & Com-
pany, New York City (2004)
13. Morey, D.: STATS basketball scoreboard, pp. 1–288 (1993)
14. Morey, L.C., Cohen, M.A.: Bias in the log5 estimation of outcome of batter/pitcher
matchups, and an alternative. J. Sports Anal. 1(1), 65–76 (2015)
15. Oliver, D.: Basketball on paper: rules and tools for performance analysis. Potomac
Books, Inc., Dulles (2004)
16. Prasetio, D., et al.: Predicting football match results with logistic regression. In:
2016 International Conference On Advanced Informatics: Concepts, Theory And
Application (ICAICTA), pp. 1–5. IEEE (2016)
17. Raizin, Sameboat: Simplified version of the summoner’s rift map. CC BY-SA
3.0 (https://creativecommons.org/licenses/by-sa/3.0/) (2013). https://commons.
wikimedia.org/w/index.php?curid=29443207
18. Saleh, H.: Machine Learning Fundamentals: Use Python and Scikit-learn to Get
Up and Running with the Hottest Developments in Machine Learning. Packt Pub-
lishing Ltd., Birmingham (2018)
19. Sevenhuysen, T.: Oracle’s elixir - LoL esports stats (2021). https://oracleselixir.
com
20. Snyder, J.: What actually wins soccer matches: prediction of the 2011–2012 premier
league for fun and profit. Thesis. University of Washington, WA: Department of
Computer Science (2013)
21. Staff, L.E.: 2019 world championship hits record viewership. https://nexus.
leagueoflegends.com/en-us/2019/12/2019-world-championship-hits-record-
viewership/. Accessed 26 Mar 2021
22. Tassi, P.: League of Legends finals sells out LA’s Staples Center in an hour. Forbes
(2013)
23. Tate, R.F.: Correlation between a discrete and a continuous variable. Point-biserial
correlation. Ann. Math. Stat. 25(3), 603–607 (1954)