Fuzzy Clustering of Batting Averages

One of the most troubling, yet intriguing aspects of Major League Baseball is the fact that there is a mind-boggling amount of statistical data for the game. Batting averages are the pinnacle example of this problem. Beyond praising the players with the largest numbers, there has never been a system for establishing valid relationships amongst every professional. Fuzzy clustering provides a sound method for grouping batting averages that would not normally be linked together, and if implemented would usher in a new wave of player management, bargaining, and scouting. With fuzzy clustering, the age-old practice of stereotyping certain defensive positions as better hitters than others is eliminated. Instead of overlooking a group of players, the entire league can be analyzed rather quickly, without sacrificing or ignoring the hitting ability of any individual. By relating each player to his colleagues, a new source of player motivation is born for managers. A struggling hitter that is grouped with the best players can be shown the data, encouraged to recognize his potential, and realize that the slump is temporary. Also, players and owners can use the fuzzy-clustered batting averages in contract negotiations: a player being able to emphasize his lofty status among professional hitters, in an attempt to increase his salary, and an owner being able to point to a prospect´s recent decline, in order to save money. Another noteworthy benefit of fuzzy clustering is the millions of dollars that could be saved in the scouting process. Traveling to see a hitter would no longer be necessary. Organizations could simply position a potential recruit amid other professionals and determine his relative ability and worth. Fuzzy clustering would forever changer Major League Baseball