A Hybrid Machine Learning Model for Predicting USA NBA All-Stars
Throughout the modern age, sports have been a very important part of human existence. As our documentation of sports has become more advanced, so have the prediction capabilities. Presently, analysts keep track of a massive amount of information about each team, player, coach, and matchup. This coll...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/1/97 |
| _version_ | 1797499238935953408 |
|---|---|
| author | Alberto Arteta Albert Luis Fernando de Mingo López Kristopher Allbright Nuria Gómez Blas |
| author_facet | Alberto Arteta Albert Luis Fernando de Mingo López Kristopher Allbright Nuria Gómez Blas |
| author_sort | Alberto Arteta Albert |
| collection | DOAJ |
| description | Throughout the modern age, sports have been a very important part of human existence. As our documentation of sports has become more advanced, so have the prediction capabilities. Presently, analysts keep track of a massive amount of information about each team, player, coach, and matchup. This collection has led to the development of unparalleled prediction systems with high levels of accuracy. The issue with these prediction systems is that they are proprietary and very costly to maintain. In other words, they are unusable by the average person. Sports, being one of the most heavily analyzed activities on the planet, should be accessible to everyone. In this paper, a preliminary system for using publicly available statistics and open-source methods for predicting NBA All-Stars is introduced and modified to improve the accuracy of the predictions, which reaches values close to 0.9 in raw accuracy, and higher than 0.9 in specificity. |
| first_indexed | 2024-03-10T03:44:37Z |
| format | Article |
| id | doaj.art-9898c8883b1c47d48157f18858835920 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T03:44:37Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-9898c8883b1c47d48157f188588359202023-11-23T11:22:50ZengMDPI AGElectronics2079-92922021-12-011119710.3390/electronics11010097A Hybrid Machine Learning Model for Predicting USA NBA All-StarsAlberto Arteta Albert0Luis Fernando de Mingo López1Kristopher Allbright2Nuria Gómez Blas3College of Arts and Sciences, Troy University, 129-A MSCX, 600 University Avenue, Troy, AL 36082, USAEscuela Técnica Superior de Ingeniería de Sistemas Informáticos, Universidad Politécnica de Madrid, 28031 Madrid, SpainCollege of Arts and Sciences, Troy University, 129-A MSCX, 600 University Avenue, Troy, AL 36082, USAEscuela Técnica Superior de Ingeniería de Sistemas Informáticos, Universidad Politécnica de Madrid, 28031 Madrid, SpainThroughout the modern age, sports have been a very important part of human existence. As our documentation of sports has become more advanced, so have the prediction capabilities. Presently, analysts keep track of a massive amount of information about each team, player, coach, and matchup. This collection has led to the development of unparalleled prediction systems with high levels of accuracy. The issue with these prediction systems is that they are proprietary and very costly to maintain. In other words, they are unusable by the average person. Sports, being one of the most heavily analyzed activities on the planet, should be accessible to everyone. In this paper, a preliminary system for using publicly available statistics and open-source methods for predicting NBA All-Stars is introduced and modified to improve the accuracy of the predictions, which reaches values close to 0.9 in raw accuracy, and higher than 0.9 in specificity.https://www.mdpi.com/2079-9292/11/1/97sports statisticssports patterns classificationsports awardsMLPrandom forestsadaboost |
| spellingShingle | Alberto Arteta Albert Luis Fernando de Mingo López Kristopher Allbright Nuria Gómez Blas A Hybrid Machine Learning Model for Predicting USA NBA All-Stars Electronics sports statistics sports patterns classification sports awards MLP random forests adaboost |
| title | A Hybrid Machine Learning Model for Predicting USA NBA All-Stars |
| title_full | A Hybrid Machine Learning Model for Predicting USA NBA All-Stars |
| title_fullStr | A Hybrid Machine Learning Model for Predicting USA NBA All-Stars |
| title_full_unstemmed | A Hybrid Machine Learning Model for Predicting USA NBA All-Stars |
| title_short | A Hybrid Machine Learning Model for Predicting USA NBA All-Stars |
| title_sort | hybrid machine learning model for predicting usa nba all stars |
| topic | sports statistics sports patterns classification sports awards MLP random forests adaboost |
| url | https://www.mdpi.com/2079-9292/11/1/97 |
| work_keys_str_mv | AT albertoartetaalbert ahybridmachinelearningmodelforpredictingusanbaallstars AT luisfernandodemingolopez ahybridmachinelearningmodelforpredictingusanbaallstars AT kristopherallbright ahybridmachinelearningmodelforpredictingusanbaallstars AT nuriagomezblas ahybridmachinelearningmodelforpredictingusanbaallstars AT albertoartetaalbert hybridmachinelearningmodelforpredictingusanbaallstars AT luisfernandodemingolopez hybridmachinelearningmodelforpredictingusanbaallstars AT kristopherallbright hybridmachinelearningmodelforpredictingusanbaallstars AT nuriagomezblas hybridmachinelearningmodelforpredictingusanbaallstars |