Jie Ke versus AlphaGo: A ranking approach using decision making method for large-scale data with incomplete information

Abstract Ranking historical players in sports is challenging since some players have never played against each other. It is even more complex in Go because of AlphaGo, a project based on artificial intelligence, who became the world's number 1 after it defeated the 528th and the 4th human Go players. AlphaGo is ranked high in the current Go ranking system because it is undefeated. The objective of this paper is to propose a new ranking method for large-scale Go players by means of incomplete fuzzy pair-wise comparison matrix whose priority vector is derived using a cosine similarity measure. Using match results provided by Go4Go.net, experiments are designed to rank top Go players in the past 45 years and examine the change in ranking after AlphaGo faced off against Jie Ke. Furthermore, the proposed method was applied to rank all 1544 Go players available at Go4Go.net to illustrate its efficiency in handling large-scale data.

[1]  Thomas L. Saaty,et al.  Rank from comparisons and from ratings in the analytic hierarchy/network processes , 2006, Eur. J. Oper. Res..

[2]  Zeshui Xu,et al.  Nonlinear Programming Model Integrating Different Preference Structures , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[3]  Francisco Herrera,et al.  Integrating multiplicative preference relations in a multipurpose decision-making model based on fuzzy preference relations , 2001, Fuzzy Sets Syst..

[4]  Lajos Rónyai,et al.  On optimal completion of incomplete pairwise comparison matrices , 2010, Math. Comput. Model..

[5]  Zhongsheng Hua,et al.  A chi-square method for obtaining a priority vector from multiplicative and fuzzy preference relations , 2007, Eur. J. Oper. Res..

[6]  Roman Słowiński,et al.  Modeling assignment-based pairwise comparisons within integrated framework for value-driven multiple criteria sorting , 2015, Eur. J. Oper. Res..

[7]  Eduardo Fernández,et al.  A method based on multiobjective optimization for deriving a ranking from a fuzzy preference relation , 2004, Eur. J. Oper. Res..

[8]  Jian Ma,et al.  An optimization approach to multiperson decision making based on different formats of preference information , 2006, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[9]  Michele Fedrizzi,et al.  Incomplete pairwise comparison and consistency optimization , 2007, Eur. J. Oper. Res..

[10]  M. Glickman.  Parameter Estimation in Large Dynamic Paired Comparison Experiments , 1999 .

[11]  Rémi Coulom,et al.  Whole-History Rating: A Bayesian Rating System for Players of Time-Varying Strength , 2008, Computers and Games.

[12]  Zeshui Xu,et al.  A least deviation method to obtain a priority vector of a fuzzy preference relation , 2005, Eur. J. Oper. Res..

[13]  José Ignacio Peláez,et al.  Estimation of missing judgments in AHP pairwise matrices using a neural network-based model , 2010, Appl. Math. Comput..

[14]  Ramakrishnan Ramanathan,et al.  A qualitative perspective to deriving weights from pairwise comparison matrices , 2010 .

[15]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[16]  Kwang-Jae Kim,et al.  Compromising prioritization from pairwise comparisons considering type I and II errors , 2010, Eur. J. Oper. Res..

[17]  László Csató,et al.  An application of incomplete pairwise comparison matrices for ranking top tennis players , 2014, Eur. J. Oper. Res..

[18]  S. H. Zanakis,et al.  A Monte Carlo investigation of incomplete pairwise comparison matrices in AHP , 1997 .

[19]  Yi-Chung Hu,et al.  Backpropagation multi-layer perceptron for incomplete pairwise comparison matrices in analytic hierarchy process , 2006, Appl. Math. Comput..

[20]  T. Saaty,et al.  The Analytic Hierarchy Process , 1985 .

[21]  Yanbing Ju,et al.  A new method for multiple criteria group decision making with incomplete weight information under linguistic environment , 2014 .

[22]  Yang Chen,et al.  Pairwise comparison matrix in multiple criteria decision making , 2016 .

[23]  Gang Kou,et al.  A cosine maximization method for the priority vector derivation in AHP , 2014, Eur. J. Oper. Res..

[24]  Teresa Wu,et al.  An intelligent decomposition of pairwise comparison matrices for large-scale decisions , 2014, Eur. J. Oper. Res..

[25]  Yi Peng,et al.  Evaluation of clustering algorithms for financial risk analysis using MCDM methods , 2014, Inf. Sci..

[26]  Louis C. K. Ma,et al.  A goal programming approach to group decision making based on multiplicative preference relations and fuzzy preference relations , 2006, Eur. J. Oper. Res..

[27]  Yin-Feng Xu,et al.  A comparative study of the numerical scales and the prioritization methods in AHP , 2008, Eur. J. Oper. Res..

[28]  Yi Peng,et al.  Estimating the missing values for the incomplete decision matrix and consistency optimization in emergency management , 2016 .

[29]  T. Tanino.  Fuzzy preference orderings in group decision making , 1984 .