Presentation 2013/3/4
Pitching tactics estimation based on probabilistic causal structure among game components learned from the MLB detailed score data
Tsukasa UEHARA, Shuichi ARAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Deterministic causal structure can not be found because of that effective tactics for baseball pitcher is a complex system. Therefore, tactical decision modeling is difficult. We propose a model of tactical decisions for pitching by learning probabilistic causal structure of the element group making up the game from a MLB scores detailed data using Bayesian Network. We have defined a characteristic and calculated the distance amount players in order to increase the number of training data. We decided the similar players distance by change the distance and perform pitching tactics estimation. Moreover, we discuss the estimation results using this model. In addition, we perform the strategy estimation using these models on various situations and show the emerging pitching strategies using this method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Datamining / Complex systems / Bayesina network
Paper # AI2012-48
Date of Issue

Conference Information
Committee AI
Conference Date 2013/3/4(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Pitching tactics estimation based on probabilistic causal structure among game components learned from the MLB detailed score data
Sub Title (in English)
Keyword(1) Datamining
Keyword(2) Complex systems
Keyword(3) Bayesina network
1st Author's Name Tsukasa UEHARA
1st Author's Affiliation Graduate School of Engineering, Tokyo City University()
2nd Author's Name Shuichi ARAI
2nd Author's Affiliation Graduate School of Engineering, Tokyo City University
Date 2013/3/4
Paper # AI2012-48
Volume (vol) vol.112
Number (no) 477
Page pp.pp.-
#Pages 6
Date of Issue