職業籃球的致勝關鍵因素-以NBA為例

NCUIR > School of Management at National Central University > Graduate Institute of Business Administration > Electronic Thesis & Dissertation > Item 987654321/85936

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/85936

Title:	職業籃球的致勝關鍵因素-以NBA為例
Authors:	周迺鈺;Chou, Nai-Yu
Contributors:	企業管理學系
Keywords:	NBA;比賽預測;決策樹;隨機森林;NBA;Game Prediction;Decision Tree;Ramdom Forest
Date:	2021-07-29
Issue Date:	2021-12-07 11:43:50 (UTC+8)
Publisher:	國立中央大學
Abstract:	近年，運動博奕事業盛行，高風險高報酬成為多數人的獲利方式，尤其是 NBA 聯盟的觀眾人數擴及全球、事業版圖跨越國界，對全世界運動有深深的影響，因此成為賭徒的主要目標。除此之外，也有許多研究者試圖預測結果和勝隊，因此有許多詳細比賽數據在網路上公開取用。而本篇論文為瞭解 NBA 主場球隊隊比賽內容並找尋規則，以 NBA 2012~2018 六年、30 隊的每場比賽詳細數據做分析，並以兩種演算法:決策樹 ( Decision Tree )，找到主場球隊比賽的勝場和敗場規則，並以隨機森林 (RandomForest)驗證能夠影響主場球隊勝場的變數之重要程度。以此預測比賽勝負並觀察勝負隊的贏球模式和輸球原因，從中找出贏球方程式，能在職業球隊選秀、比賽戰術運用、球員交易等不同面向，或者在一般觀賞或者運動彩券等不同領域有所應用。;In the recent year, sport betting industry is more popular nowadays, and the way of high risk with high return become a main way investment for more and more people. Especially NBA, it is the main target for professional gambler because it attracts audience from all the world and its business territory has been all over the world. So, there are uncountable researchers trying to analyze and predict the winning team for personal or business. Moreover, there are a lot of data of detailed contents of games on websites for people to research and analyze. And, the dataset in this paper is from www.kaggle.com.tw. In this paper, I collect data of NBA 30-team-games from 2012 to 2018, analyzing by 2 algorithms. As the result, I found out the rule of winning of home team by decision tree and test the level of importance by random forest, trying to figure out the formula of winning and the reason of losing, also, predicting the result of games. In sum, the result of research could be used in a variety of fields, like draft, games tactics, players trading, watching games, and betting.
Appears in Collections:	[Graduate Institute of Business Administration] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	100	View/Open

社群 sharing

Loading...