東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Using Machine Learning to Predict th...

Burson, R. J.,

FindBook

Google Book

Amazon

博客來

Using Machine Learning to Predict the Next Pitch of an MLB Game /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Using Machine Learning to Predict the Next Pitch of an MLB Game // R. J Burson.
作者:	Burson, R. J.,
面頁冊數:	1 electronic resource (113 pages)
附註:	Source: Masters Abstracts International, Volume: 86-04.
Contained By:	Masters Abstracts International86-04.
標題:	Statistics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31336501
ISBN:	9798384481140

Using Machine Learning to Predict the Next Pitch of an MLB Game /
Burson, R. J.,

Using Machine Learning to Predict the Next Pitch of an MLB Game /R. J Burson. - 1 electronic resource (113 pages)

Source: Masters Abstracts International, Volume: 86-04.

Major League Baseball (MLB) is one of the four major North American sports, and the use of statistics in the sport has become increasingly popular in recent decades. In 1971 the Society of American Baseball Research (SABR) was founded and in 1977 Bill James published his first Baseball Abstract. In the present day, every MLB team has an analytics department to try and gain advantages on the field. The goal of this project is to predict the upcoming pitch of an MLB game using MLB's Baseball Savant pitch-by-pitch data. There have been multiple research papers on pitch prediction with promising results, but this paper's goal is to improve on past research of pitch prediction. Many of the previous models only attempted to classify pitches binarily into fastball or non-fastball categories. To improve the usefulness compared to previous models this paper will attempt to classify a pitch into each possible pitch that a pitcher has in his arsenal. (Fastball, Slider, Changeup, etc.) This paper will show how various models such as multinomial logistic regression, random forest, and k-nearest neighbor (KNN) models were built to try and predict the next pitch based on the game-state situation and the players involved. The paper also presents how our model performed on every pitcher but also on different pitcher groupings that we believed could have affected the model's accuracy. Our best model was a standard KNN model that reached an overall predictive accuracy of 64.59%.

English

ISBN: 9798384481140Subjects--Topical Terms:

517247
Statistics.
Subjects--Index Terms:

Major League Baseball

Using Machine Learning to Predict the Next Pitch of an MLB Game /
LDR:02866nmm a22004213i 4500 001 2436026
005 20251021115058.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798384481140
035 $a (MiAaPQD)AAI31336501
035 $a AAI31336501
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Burson, R. J., $e author. $3 3826539
245 1 0 $a Using Machine Learning to Predict the Next Pitch of an MLB Game / $c R. J Burson.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (113 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 86-04.
500 $a Advisors: Suaray, Kagba N. Committee members: Korosteleva, Olga; Safer, Alan.
502 $b M.S. $c California State University, Long Beach $d 2024.
520 $a Major League Baseball (MLB) is one of the four major North American sports, and the use of statistics in the sport has become increasingly popular in recent decades. In 1971 the Society of American Baseball Research (SABR) was founded and in 1977 Bill James published his first Baseball Abstract. In the present day, every MLB team has an analytics department to try and gain advantages on the field. The goal of this project is to predict the upcoming pitch of an MLB game using MLB's Baseball Savant pitch-by-pitch data. There have been multiple research papers on pitch prediction with promising results, but this paper's goal is to improve on past research of pitch prediction. Many of the previous models only attempted to classify pitches binarily into fastball or non-fastball categories. To improve the usefulness compared to previous models this paper will attempt to classify a pitch into each possible pitch that a pitcher has in his arsenal. (Fastball, Slider, Changeup, etc.) This paper will show how various models such as multinomial logistic regression, random forest, and k-nearest neighbor (KNN) models were built to try and predict the next pitch based on the game-state situation and the players involved. The paper also presents how our model performed on every pitcher but also on different pitcher groupings that we believed could have affected the model's accuracy. Our best model was a standard KNN model that reached an overall predictive accuracy of 64.59%.
546 $a English
590 $a School code: 6080
650 4 $a Statistics. $3 517247
650 4 $a Sports management. $3 3423935
650 4 $a American studies. $3 2122720
653 $a Major League Baseball
653 $a Machine learning
653 $a North American sports
653 $a K-nearest neighbor
690 $a 0463
690 $a 0323
690 $a 0430
710 2 $a California State University, Long Beach. $b Mathematics and Statistics. $e degree granting institution. $3 3819208
720 1 $a Suaray, Kagba N. $e degree supervisor.
773 0 $t Masters Abstracts International $g 86-04.
790 $a 6080
791 $a M.S.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31336501