Supervised Learning models with ice hockey data
The technology developments of the last years allow measuring data in almost every field and area nowadays, especially increasing the potential for analytics in branches in which not much analytics have been done due to complicated data access before. The increased number of interest in sports analy...
Main Author: | |
---|---|
Format: | Others |
Language: | English |
Published: |
Linköpings universitet, Statistik och maskininlärning
2019
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-167718 |
id |
ndltd-UPSALLA1-oai-DiVA.org-liu-167718 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-UPSALLA1-oai-DiVA.org-liu-1677182020-12-18T05:32:38ZSupervised Learning models with ice hockey dataengÁlvarez Robles, Enrique JosuéLinköpings universitet, Statistik och maskininlärning2019StatisticsMachine learningNeural NetworksSupervised LearningTensorflowDeep LearningProbability Theory and StatisticsSannolikhetsteori och statistikComputer SciencesDatavetenskap (datalogi)The technology developments of the last years allow measuring data in almost every field and area nowadays, especially increasing the potential for analytics in branches in which not much analytics have been done due to complicated data access before. The increased number of interest in sports analytics is highly connected to the better technology now available for visual and physical sensors on the one hand and sports as upcoming economic topic holding potentially large revenues and therefore investing interest on the other hand. With the underlying database, precise strategies and individual performance improvements within the field of professional sports are no longer a question of (coach)experience but can be derived from models with statistical accuracy. This thesis aims to evaluate if the available data together with complex and simple supervised machine learning models could generalize from the training data to unseen situations by evaluating performance metrics. Data from games of the ice hockey team of Linköping for the season 2017/2018 is processed with supervised learning algorithms such as binary logistic regression and neural networks. The result of this first step is to determine the strategies of passes by considering both, attempted but failed and successful shots on goals during the game. For that, the original, raw data set was aggregated to game-specific data. After having detected the distinct strategies, they are classified due to their rate of success. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-167718application/pdfinfo:eu-repo/semantics/openAccess |
collection |
NDLTD |
language |
English |
format |
Others
|
sources |
NDLTD |
topic |
Statistics Machine learning Neural Networks Supervised Learning Tensorflow Deep Learning Probability Theory and Statistics Sannolikhetsteori och statistik Computer Sciences Datavetenskap (datalogi) |
spellingShingle |
Statistics Machine learning Neural Networks Supervised Learning Tensorflow Deep Learning Probability Theory and Statistics Sannolikhetsteori och statistik Computer Sciences Datavetenskap (datalogi) Álvarez Robles, Enrique Josué Supervised Learning models with ice hockey data |
description |
The technology developments of the last years allow measuring data in almost every field and area nowadays, especially increasing the potential for analytics in branches in which not much analytics have been done due to complicated data access before. The increased number of interest in sports analytics is highly connected to the better technology now available for visual and physical sensors on the one hand and sports as upcoming economic topic holding potentially large revenues and therefore investing interest on the other hand. With the underlying database, precise strategies and individual performance improvements within the field of professional sports are no longer a question of (coach)experience but can be derived from models with statistical accuracy. This thesis aims to evaluate if the available data together with complex and simple supervised machine learning models could generalize from the training data to unseen situations by evaluating performance metrics. Data from games of the ice hockey team of Linköping for the season 2017/2018 is processed with supervised learning algorithms such as binary logistic regression and neural networks. The result of this first step is to determine the strategies of passes by considering both, attempted but failed and successful shots on goals during the game. For that, the original, raw data set was aggregated to game-specific data. After having detected the distinct strategies, they are classified due to their rate of success. |
author |
Álvarez Robles, Enrique Josué |
author_facet |
Álvarez Robles, Enrique Josué |
author_sort |
Álvarez Robles, Enrique Josué |
title |
Supervised Learning models with ice hockey data |
title_short |
Supervised Learning models with ice hockey data |
title_full |
Supervised Learning models with ice hockey data |
title_fullStr |
Supervised Learning models with ice hockey data |
title_full_unstemmed |
Supervised Learning models with ice hockey data |
title_sort |
supervised learning models with ice hockey data |
publisher |
Linköpings universitet, Statistik och maskininlärning |
publishDate |
2019 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-167718 |
work_keys_str_mv |
AT alvarezroblesenriquejosue supervisedlearningmodelswithicehockeydata |
_version_ |
1719370816971341824 |