Modeling Baseball Outcomes as Higher-Order Markov Chains

Abstract

Baseball is one of the few sports in which each team plays a game nearly everyday. For instance, in the baseball league in South Korea, namely the KBO (Korea Baseball Organization) league, every team has a game everyday except for Mondays. This consecutiveness of the KBO league schedule could make a team's match outcome be associated to the results of recent games. This paper deals with modeling the match outcomes of each of the ten teams in the KBO league as a higher-order Markov chain, where the possible states are win ($"W"$), draw ($"D"$), and loss ($"L"$). For each team, the value of $k$ in which the $k^{\text{th}}$ order Markov chain model best describes the match outcome sequence is computed. Further, whether there are any patterns between such a value of k and the team's overall performance in the league is examined. We find that for the top three teams in the league, lower values of $k$ tend to have the $k^{th}$ order Markov chain to better model their outcome, but the other teams don't reveal such patterns.