Predicting NBA games outcome Using Artificial Neural Network

```Predicting
Outcome of
NBA Games
Using Artificial
Neural Network
Yung-Hsien Chu
Background
 National
league that includes 30 clubs.
 Many experts, gambling websites, and
even fans themselves are trying to make
prediction to NBA games.
Development of Prediciton
Methods
 Originally,
gamblers predict NBA games
with their own experiences and instincts.
 In recent years, especially after the MLB
Sabermetrics mania, experts and
gamblers started to develop similar
method and using some form of
computer models to support their
predictions.
Project Goal
 This
project aims to predict outcome of
NBA games based mostly on the statistics
numbers, be it traditional statistics like
point per game (PPG), or advanced
statistics like True Shooting Percentage
(TS%). Other possible features including
injury status, team chemistry, and fatigue
factor.
Data Collection
 All
 The reason I choose this site is because
this site provides not only traditional data,
but also advanced data such as TS% and
Turnover Percentage (TOV%).
 Another advantage of this website is it
allows its data to be converted to CSV
form for data processing.
Neuron Network Choice
 Back-propagation



multilayer perceptron
Supervised learning – win/lose outcome
classification
Non-linear
Flexibility to process large amount of data.
Difficulties encountered so far




There are many non-statistic factors that can have
a great impact on the game outcome: injuries,
rumors, and “team chemistry”.
Team composition changes a lot between each
year or even during basketball season due to
Even though there are advanced statistics, many
are still questioning whether or not they can
represent the ability of a player or team.
Basketball is a sport that involving heavy
interaction between players, so far there is no
related data to represent it.
Project Expectation
 58%
accuracy should be expected, since
it is the common percentage a normal
gambler could achieve.
 70% accuracy would be the ultimate
goal, best analyzers and gamblers are
known to have accuracy around 70%.
(ESPN: 68.3%, Bob Voulgaris: Around 70%)
Reference



Miljkovic, D., et al. &quot;The use of data mining for