Boltzmann and Fokker-Planck equations modelling the Elo rating system with learning effects

DOI10.1007/S00332-018-9512-8MaRDI QIDQ2003403zbMATH OpenOpenAlexWikidataFDO

Authors Bertram Düring, Marco Torregrossa, M-T Wolfram

Publication date 8 July 2019

Published in Journal of Nonlinear Science (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1806.06648

zbMATH Keywords

asymptotic behaviourElo ratingexistence of weak solutionsFokker-Planck equationkinetic modellearning

Mathematics Subject Classification ID

Asymptotic behavior of solutions to PDEs (35B40) Weak solutions to PDEs (35D30) Degenerate parabolic equations (35K65) Boltzmann equations (35Q20) Fokker-Planck equations (35Q84) PDEs in connection with game theory, economics, social and behavioral sciences (35Q91) Monte Carlo methods (65C05) Numerical methods (including Monte Carlo methods) (91G60)

Abstract: In this paper we propose and study a new kinetic rating model for a large number of players, which is motivated by the well-known Elo rating system. Each player is characterised by an intrinsic strength and a rating, which are both updated after each game. We state and analyse the respective Boltzmann type equation and derive the corresponding nonlinear, nonlocal Fokker-Planck equation. We investigate the existence of solutions to the Fokker-Planck equation and discuss their behaviour in the long time limit. Furthermore, we illustrate the dynamics of the Boltzmann and Fokker-Planck equation with various numerical experiments.

Review text

The authors introduce a generalisation of the kinetic Elo model in competitor versus competitor games in which the rating and intrinsic strength of the players change in time and the dynamics are driven by the microscopic binary interactions. They derive the corresponding Fokker-Planck-type equation as the quasi-invariant limit of the Boltzmann-type model. The existence of solutions to the Fokker-Planck equation and their behaviour in the long time limit are investigated. Various numerical simulations of the Boltzmann and the Fokker-Planck equations are finally presented.

Recommendations

• A continuous model for ratings
• Fokker-Planck equations in the modeling of socio-economic phenomena
• Local contractivity of the process of a player rating variation in the Elo model with one adversary
• Stationary distribution of the player rating in the Elo model with one adversary
• Elo ratings and the sports model: a neglected topic in applied probability?

Cites work

• A continuous model for ratings
• A kinetic equation for economic value estimation with irrationality and herding
• A mathematical model for value estimation with public information and herding
• Boltzmann and Fokker-Planck equations modelling opinion formation in the presence of strong leaders
• Boltzmann-type control of opinion consensus through leaders
• Compact sets in the space L^ p(0,T;B)
• Evolution of wealth in a non-conservative economy driven by local Nash equilibria
• Heterophilious dynamics enhances consensus
• scientific article; zbMATH DE number 42636 (Why is no real title available?)
• Interacting multiagent systems. Kinetic equations and Monte Carlo methods
• Kinetic models of opinion formation
• Large-time behavior in non-symmetric Fokker-Planck equations
• Mesoscopic modelling of financial markets
• On a Boltzmann mean field model for knowledge growth
• On a Boltzmann-type price formation model
• On the dynamics of social conflicts: looking for the black swan
• Opinion dynamics: inhomogeneous Boltzmann-type equations modelling opinion leadership and political segregation
• The Boltzmann equation and its applications
• The mathematical theory of dilute gases
• Wealth distribution and collective knowledge: a Boltzmann approach
• Wealth distribution in presence of debts: a Fokker-Planck description

Cited in

(12)

• Propagation of chaos: a review of models, methods and applications. II: Applications
• Continuum and thermodynamic limits for a simple random-exchange model
• Monte Carlo stochastic Galerkin methods for non-Maxwellian kinetic models of multiagent systems with uncertainties
• The impact of intelligent transportation points system based on Elo rating on emergence of cooperation at Y intersection
• Stationary distribution of the player rating in the Elo model with one adversary
• Local contractivity of the process of a player rating variation in the Elo model with one adversary
• A continuous model for ratings
• Swarming: hydrodynamic alignment with pressure
• Trends to equilibrium for a nonlocal Fokker-Planck equation
• Steady states of an Elo-type rating model for players of varying strength
• Opinion dynamics for an increasing population of agents: a symmetric continuous agent model
• Convergence and stationary distribution of Elo rating systems

This page was built for publication: Boltzmann and Fokker-Planck equations modelling the Elo rating system with learning effects

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2003403)