SPORTS ANALYTICS

INTRODUCTION:
Over the past years, a variety of data-capturing technologies have become
available in sport business. These technologies allow sport management
businesses to capture and collect data on games, bidding, bookmaker odds,
playing styles, scores, and many other sport attributes. Such a repository of data
allows firms to garner invaluable insights through the leveraging of data
analytics. There have also been several discussions around this issue in literary
and business circles . The studies suggest that a data-driven approach to sport
business and marketing is an interesting area to investigate. In this context, data
analytics could be of immense value.

Data analytics in sport has become an integral part of sport business . Data
mining-based models are also being explored in sport . Other forms of analytical
techniques being explored include, page rank models, numerical algorithms and
machine learning .

Recently, the Fédération Internationale de Football Association approved the

use of Electronic Performance and Tracking Systems (EPTS) during
competition. Now, the physical data collected using EPTS, from both training
sessions and live matches, can be used to evaluate the extent to which match
performance can be predicted . Scholars have proposed a normalised root mean
square error metric for analysing the results obtained from the application of
machine-learning algorithms to the data collected for various physical variables.
Specific physical variables can also act as representatives of several other
variables, which are highly correlated, to further reduce the number of variables
that must be periodically analysed by coaches . Moreover, continuously growing
sports platforms related to games incentivize bookies and bettors to bet on
match results as a game changes ball by ball. Hence, attempts have been made
to predict match results based on historical match data.

Further, the emotional expressions of sports team members, and their correlation
with the team’s performance, can be analysed to draw conclusions about the
psychological mind-set of players . Design of experiments, is applied to frame
experiments explain the variation under certain conditions to predict the
outcome in certain variables . Finally, researchers have introduced variables
such as possession (ball occupation) and territory (dominance of territory) and a
novel visual analytics system to analyse tactical transitions in a continuous ball
match .

SPORTS ANALYTICS:
Sports analytics are a collection of relevant, historical, statistics that
can provide a competitive advantage to a team or individual. Through
the collection and analyzation of these data, sports analytics inform
players, coaches and other staff in order to facilitate decision making
both during and prior to sporting events. The term "sports analytics"
was popularized in mainstream sports culture following the release of
the 2011 film, Moneyball, in which Oakland Athletics General
Manager Billy Bean (played by Brad Pitt) relies heavily on the use of
analytics to build a competitive team on a minimal budget.
There are two key aspects of sports analytics — on-field and off-field
analytics. On-field analytics deals with improving the on-field
performance of teams and players, including questions such as "which
player on the Red Sox contributed most to the team's offense?" or
"who is the best wing player in the NBA?", etc. Off-field analytics deals
with the business side of sports. Off-field analytics focuses on helping a
sport organization or body surface patterns and insights through data
that would help increase ticket and merchandise sales, improve fan
engagement, etc. Off-field analytics essentially uses data to help rights
holders take decisions that would lead to higher growth and increased
profitability.
As technology has advanced over the last number of years data
collection has become more in-depth and can be conducted with
relative ease. Advancements in data collection have allowed for sports
analytics to grow as well, leading to the development of advanced
statistics and machine learning, as well as sport specific technologies
that allow for things like game simulations to be conducted by teams
prior to play, improve fan acquisition and marketing strategies, and
even understand the impact of sponsorship on each team as well as its
fans.
Another significant impact sports analytics have had on professional
sports is in relation to sport gambling. In depth sports analytics have
taken sports gambling to new levels, whether it be fantasy sports
leagues or nightly wagers, bettors now have more information at their
disposal to help aid decision making. A number of companies and
webpages have been developed to help provide fans with up to the
minute information for their betting needs.
HISTORY OF CRICKET:

Early Cricket (Pre 1799)

Cricket On The Artillery Ground

There is a consensus of expert opinion that cricket may have been invented during Saxon or
Norman times by children living in the Weald, an area of dense woodlands and clearings in south-
east England. The first reference to cricket being played as an adult sport was in 1611, and in the
same year, a dictionary defined cricket as a boys' game. There is also the thought that cricket may
have derived from bowls, by the intervention of a batsman trying to stop the ball from reaching its
target by hitting it away.

Village cricket had developed by the middle of the 17th century and the first English “county teams”
were formed in the second half of the century, as “local experts” from village cricket were employed
as the earliest professionals. The first known game in which the teams use county names is in
1709.
Early village cricket
In the first half of the 18th Century cricket established itself as a leading sport in London and the
south-eastern counties of England. Its spread was limited by the constraints of travel, but it was
slowly gaining popularity in other parts of England and Women’s Cricket dates back to the 1745,
when the first known match was played in Surrey.

In 1744, the first Laws of Cricket were written and subsequently amended in 1774, when innovations
such as lbw, a 3rd stump, - the middle stump and a maximum bat width were added. The codes
were drawn up by the “Star and Garter Club” whose members ultimately founded the famous
Marylebone Cricket Club at Lord's in 1787. MCC immediately became the custodian of the Laws and
has made revisions ever since then to the current day.
The first instances of cricket
Rolling the ball along the ground was superseded sometime after 1760 when bowlers began to pitch
the ball and in response to that innovation the straight bat replaced the old “hockey-stick” style of
bat. The Hambledon Club in Hampshire was the focal point of the game for about thirty years until
the formation of MCC and the opening of Lord's Cricket Ground in 1787.

Cricket was introduced to North America via the English colonies as early as the 17th century, and in
the 18th century it arrived in other parts of the globe. It was introduced to the West Indies by
colonists and to India by British East India Company mariners. It arrived in Australia almost as soon
as colonisation began in 1788 and the sport reached New Zealand and South Africa in the early
years of the 19th century.

METHODOLOGY:
This research attempts to evaluate different machine learning

techniques to the problem of predicting the outcome of IPL cricket

matches. We design intelligent models to predict a match outcome

based on the impact of home ground and toss winner respectively.

The team that wins the toss contemplates factors such as weather,

pitch and outfield to decide whether to bat or field first, with the

intention of securing a strategic advantage. Two models are formu-

lated in this paper, one depicting the impact of home ground and

the other considering the effect of toss decision. The former consid-

ers 6 variables and the latter, 7 variables.

Fig. 1 depicts the framework of cricket match intelligent mod-

els. Initially, the input dataset is pre-processed by eliminating

any incomplete records so that there are no missing values in the

dataset. Data with no match result were excluded from the classi-

fication (5 instances). More importantly, we eliminate features that

have no direct impact on the performance of the training phase by

applying feature selection. Features including Match ID, Match

date and Venue among others have been discarded prior to the

training phase of the machine learning techniques (more details

are given in Section 4). Once the input dataset has been pre-

processed, it is split into two features sets; one feature set that con-

cerns features related to the home ground and another one for the

toss decision features.

Once the dataset is split, a number of different learning algo-

rithms are applied on the two feature sets to derive predictive

models for the match result. The testing methods used to derive

the classifiers is ten-fold cross validation with stratification [32].

These models are then compared to seek the one(s) that can be uti-

lized for forecasting upcoming matches results. The machine learn-

ing algorithms that have been implemented to derive the predictive models are Naïve
Bayes, Random Forest, K-nearest
neighbour and Model Decision Tree. The choice of these methods

is based on the diverse learning they adopt to develop the models.

DATA AND RESULT ANALYTICS:

PROBLEM:
India’s most popular game is cricket. There are more number of players in india.
Than other countries. But quality cricket teams are lesser in the world. Comparing to
football cricket has less participating nations. Because many countries are
concentrating only in the Olympics games. Cricket is not in the Olympics so they are not
accepting crick