Kelly Rohrer, Jacob Ziller, Alanna Flores, W. Scherer, Christopher Kaylor, Orlando Jimenez, Stephen Adams
{"title":"Developing State-Based Recommendation Systems for Golf Training","authors":"Kelly Rohrer, Jacob Ziller, Alanna Flores, W. Scherer, Christopher Kaylor, Orlando Jimenez, Stephen Adams","doi":"10.1109/SIEDS49339.2020.9106646","DOIUrl":null,"url":null,"abstract":"The NBA, MLB, NFL and other professional leagues utilize sports analytics, but the potential of professional golf analytics is largely untapped. Instead of using data-driven methods connecting practice to tournament performance, training regimens are often based on conventional wisdom. How can data be used to recommend training regimens for golfers to improve performance? We partnered with golf analytics company, GameForge, to develop tools and methods for golf analytics to capture these markets, including the development of a state-based training recommendation system. We used Gameforge, PGA, and LPGA data to build markov models using k-means clustering, and linear models. These two model types form the basis of our recommendation system. In the future, these methods can be used to inform training decisions, particularly as more data is collected.","PeriodicalId":331495,"journal":{"name":"2020 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 Systems and Information Engineering Design Symposium (SIEDS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SIEDS49339.2020.9106646","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The NBA, MLB, NFL and other professional leagues utilize sports analytics, but the potential of professional golf analytics is largely untapped. Instead of using data-driven methods connecting practice to tournament performance, training regimens are often based on conventional wisdom. How can data be used to recommend training regimens for golfers to improve performance? We partnered with golf analytics company, GameForge, to develop tools and methods for golf analytics to capture these markets, including the development of a state-based training recommendation system. We used Gameforge, PGA, and LPGA data to build markov models using k-means clustering, and linear models. These two model types form the basis of our recommendation system. In the future, these methods can be used to inform training decisions, particularly as more data is collected.