Fusing non-conservative kinetic market models and evolutionary computing

Abstract This research establishes an identity between kinetic market models of econophysics and evolutionary algorithms of computer science. The fusion between the two approaches motivated a new market model with two basic operations: sampling and selection of states. The result is a non-conservative market that depends on the size of the sample set and the approach used to approximate the principle of energy conservation. This market exhibits complex dynamics with random walks for the sum of all the agents’ money and a scaling behavior for the money distribution in the population. Moreover, the fusion demonstrates how to add an evolutionary context to the kinetic market models and suggests a quasi-equilibrium version of those models. As a by-product, the work reveals a practical application as a new replacement rule for family competition evolutionary algorithms, which outperforms traditional ones in challenging combinatorial optimization problems.

[1]  Fardin Ahmadizar,et al.  Artificial neural network development by means of a novel combination of grammatical evolution and genetic algorithm , 2015, Eng. Appl. Artif. Intell..

[2]  Marjan Mernik,et al.  Exploration and exploitation in evolutionary algorithms: A survey , 2013, CSUR.

[3]  Wayne Iba,et al.  Population Diversity as a Selection Factor: Improving Fitness by Increasing Diversity , 2016, GECCO.

[4]  G. Toscani,et al.  Self-Similarity and Power-Like Tails in Nonconservative Kinetic Models , 2010, 1009.2760.

[5]  David E. Goldberg,et al.  Alleles, loci and the traveling salesman problem , 1985 .

[6]  V. Yakovenko,et al.  Colloquium: Statistical mechanics of money, wealth, and income , 2009, 0905.1518.

[7]  Shahryar Rahnamayan,et al.  Metaheuristics in large-scale global continues optimization: A survey , 2015, Inf. Sci..

[8]  Bikas K. Chakrabarti,et al.  Pareto Law in a Kinetic Model of Market with Random Saving Propensity , 2004 .

[9]  L. Darrell Whitley,et al.  An overview of evolutionary algorithms: practical issues and common pitfalls , 2001, Inf. Softw. Technol..

[10]  Enrique Alba,et al.  Improving Diversity in Evolutionary Algorithms: New Best Solutions for Frequency Assignment , 2017, IEEE Transactions on Evolutionary Computation.

[11]  Dirk Thierens,et al.  Elitist recombination: an integrated selection recombination GA , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[12]  Andrés Faiña,et al.  An evolution friendly modular architecture to produce feasible robots , 2015, Robotics Auton. Syst..

[13]  Per Kristian Lehre,et al.  Escaping Local Optima Using Crossover With Emergent Diversity , 2018, IEEE Transactions on Evolutionary Computation.

[14]  Joseph Persky,et al.  Retrospectives: Pareto's Law , 1992 .

[15]  Fearghal Morgan,et al.  Maintaining Healthy Population Diversity Using Adaptive Crossover, Mutation, and Selection , 2011, IEEE Transactions on Evolutionary Computation.

[16]  Giovanni Squillero,et al.  Divergence of character and premature convergence: A survey of methodologies for promoting diversity in evolutionary optimization , 2016, Inf. Sci..

[17]  G. Toscani,et al.  Explicit equilibria in a kinetic model of gambling. , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[18]  Ankit Chaudhary,et al.  A comparative review of approaches to prevent premature convergence in GA , 2014, Appl. Soft Comput..

[19]  Victor M. Yakovenko,et al.  Statistical mechanics of money , 2000 .

[20]  Juan Julián Merelo Guervós,et al.  Analysing the influence of the fitness function on genetically programmed bots for a real-time strategy game , 2017, Entertain. Comput..

[21]  M. Nowak,et al.  Unifying evolutionary dynamics. , 2002, Journal of theoretical biology.

[22]  Scott D. Goodwin,et al.  Convergence characteristics of keep-best reproduction , 1999, SAC '99.

[23]  Mohammed Azmi Al-Betar,et al.  Taming the 0/1 knapsack problem with monogamous pairs genetic algorithm , 2016, Expert Syst. Appl..

[24]  Francisco Herrera,et al.  Replacement strategies to preserve useful diversity in steady-state genetic algorithms , 2008, Inf. Sci..

[25]  H. Jaeger,et al.  Granular solids, liquids, and gases , 1996 .

[26]  S. Redner,et al.  Wealth distributions in asset exchange models , 1998, 1006.4595.

[27]  M.N.S. Swamy,et al.  Search and Optimization by Metaheuristics: Techniques and Algorithms Inspired by Nature , 2016 .

[28]  Ole J Mengshoel,et al.  The Crowding Approach to Niching in Genetic Algorithms , 2008, Evolutionary Computation.

[29]  Samir W. Mahfoud.  Crowding and Preselection Revisited , 1992, PPSN.

[30]  Yuichi Nagata.  Population Diversity Measures Based on Variable-Order Markov Models for the Traveling Salesman Problem , 2016, PPSN.

[31]  Carlos Segura,et al.  The Importance of Proper Diversity Management in Evolutionary Algorithms for Combinatorial Optimization , 2015, NEO.

[32]  Ole J. Mengshoel,et al.  Adaptive generalized crowding for genetic algorithms , 2014, Inf. Sci..

[33]  S. Salcedo-Sanz.  Modern meta-heuristics based on nonlinear physics processes: A review of models and design procedures , 2016 .

[34]  David E. Goldberg,et al.  Probabilistic Crowding: Deterministic Crowding with Probabilistic Replacement , 1999 .

[35]  Joaquín Cerdá,et al.  LGEM: A lattice Boltzmann economic model for income distribution and tax regulation , 2013, Math. Comput. Model..

[36]  Bikas K. Chakrabarti,et al.  Statistical mechanics of money: how saving propensity affects its distribution , 2000, cond-mat/0004256.

[37]  Sigrún Andradóttir,et al.  A Review of Random Search Methods , 2015 .

[38]  M. Yamamura,et al.  A functional specialization hypothesis for designing genetic algorithms , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[39]  F. Slanina.  Inelastically scattering particles and wealth distribution in an open economy. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[40]  Marco Patriarca,et al.  Kinetic models of immediate exchange , 2014, 1505.01274.

[41]  Robert A. Nye.  The influences of evolutionary theory on Pareto's sociology , 1986 .

[42]  Gerhard Reinelt,et al.  TSPLIB - A Traveling Salesman Problem Library , 1991, INFORMS J. Comput..

[43]  Joshua M. Epstein,et al.  Growing Artificial Societies: Social Science from the Bottom Up , 1996 .

[44]  Hojjat Adeli,et al.  Shape optimization of free-form steel space-frame roof structures with complex geometries using evolutionary computing , 2015, Eng. Appl. Artif. Intell..

[45]  Nizam Omar,et al.  Rethinking exchange market models as optimization algorithms , 2018 .

[46]  Jonathan H. Turner,et al.  Returning the “Social” to Evolutionary Sociology: Reconsidering Spencer, Durkheim, and Marx’s Models of “Natural” Selection , 2017 .

[47]  Dongyang Li,et al.  A Novel Strategy to Control Population Diversity and Convergence for Genetic Algorithm , 2017, ICSI.