Particle swarm optimization approach to portfolio optimization

Cura, Tunchan

doi:10.1016/j.nonrwa.2008.04.023

Cited by 226 publications

(159 citation statements)

References 13 publications

Supporting

Mentioning

144

Contrasting

Unclassified

Order By: Relevance

“…Generational distance (GD) (Cura, 2009) refers to the average minimum distance of each portfolio on the CEF from the UEF, calculated using Formula (12) where d x * x is the Euclidean distance. f v and f r are the risk (Eq.…”

Section: Analysis On Different Constraints In the MV Modelmentioning

confidence: 99%

Constrained Portfolio Optimisation: The State-of-the-Art Markowitz Models

Jin

Atkin

2016

Proceedings of 5th the International Conference on Operations Research and Enterprise Systems

View full text Add to dashboard Cite

Abstract:This paper studies the state-of-art constrained portfolio optimisation models, using exact solver to identify the optimal solutions or lower bound for the benchmark instances at the OR-library with extended constraints. The effects of pre-assignment, round-lot, and class constraints based on the quantity and cardinality constrained Markowitz model are firstly investigated to gain insights of increased problem difficulty, followed by the analysis of various constraint settings including those mostly studied in the literature. The study aims to provide useful guidance for future investigations in computational algorithms.

show abstract

Section: Analysis On Different Constraints In the MV Modelmentioning

confidence: 99%

Constrained Portfolio Optimisation: The State-of-the-Art Markowitz Models

Jin

Atkin

2016

Proceedings of 5th the International Conference on Operations Research and Enterprise Systems

View full text Add to dashboard Cite

show abstract

“…But in experimental may this condition not established. This model is a quadratic programming problem, for solving this model does not exit effective algorithms [1,2], because of this sake we use the PSO algorithm.…”

Section: Portfolio Selection Problemmentioning

confidence: 99%

“…They are stochastic search techniques based on the principles and policies of natural genetics and selection. The policy of genetic algorithms is that they start with a population of randomly generated particles and evolve towards better solutions by applying genetic operators, such as crossover and mutation, modeled on natural genetic inheritance and Darwinian survival of the fittest [1,2]. As in [3] the proposed GA for solving portfolio optimization is stated below:…”

Section: Ga Algorithm For Portfolio Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

Portfolio Optimization Using Particle Swarm Optimization And Genetic Algorithm

Kamali¹

2014

J. Math. Computer Sci.

View full text Add to dashboard Cite

This study basically employs the Markowitz mean-variance model for portfolio selection problem. Since this model is classified as a quadratic programming model there is not any efficient algorithm to solve it. The goal of this study is to find a feasible portfolio with a minimum risk through the application of heuristic algorithm. The two PSO and GA algorithm has been used. The results show that PSO approach is suitable in portfolio optimization.

show abstract

“…Consequently, numerous papers are published that resort to metaheuristic algorithms which seem more appropriate to handle them [16][17][18][19][20][21][22] .…”

mentioning

confidence: 99%

Portfolio Optimization with Metaheuristics

Mamanis¹

2017

View full text Add to dashboard Cite

Portfolio optimization is the problem of searching for an optimal allocation of wealth to put in the available assets. Since the seminal work done by Markowitz, the problem is codified as a two-objective mean-risk optimization problem where the best trade-off solutions (portfolios) between risk (measured by variance) and mean are hunted. Complex measures of risk (e.g., value-at-risk, expected shortfall, semivariance), added objective functions (e.g., maximization of skewness, liquidity, dividends) and pragmatic, real-world constraints (e.g., cardinality constraints, quantity constraints, minimum transaction lots, class constraints) that are included in recent portfolio selection models, provide many optimization challenges. The resulting portfolio optimization problem becomes very hard to be tackled with exact techniques as it displays nonlinearities, discontinuities and high dimensional efficient frontiers. These characteristics prompted a lot of researchers to explore the use of metaheuristics, which are powerful techniques for discovering near optimal solutions (sometimes the real optimum) for hard optimization problems in acceptable computational time. This report provides a brief note on the field of portfolio optimization with metaheuristics and concludes that especially Multiobjective metaheuristics (MOMHs) provide a natural background for dealing with portfolio selection problems with complex measures of risk (which define non-convex, non-differential objective functions), discrete constraints and multiple objectives.Keywords: Metaheuristics; Multiobjective optimization; Portfolio selection Portfolio Optimization with MetaheuristicsPortfolio optimization is an active area of research within finance. In general, the problem consists of searching for an optimal allocation of the available capital among various assets. A crucial solution to this problem was given by Harry Markowitz who proposed the mean-variance model for portfolio choice [1,2] . Under the mean-variance model the solution to the problem of portfolio choice is to find the best trade-off portfolios between expected return (mean) and risk which is measured by variance. The expected return is maximized while variance is simultaneously minimized.Finding these trade-off portfolios requires solving a multiobjective nonlinear otptimization problem. These portfolios define a special solution set which is very crucial in portfolio theory. This set is called efficient in portfolio's theory parlance. The image of this set in mean-variance space defines the so called efficient frontier [3] . Generating the exact efficient set and the resulting efficient frontier for the mean-variance portfolio optimization model, a few techniques exist, which can solve examples with more than 2000 assets [4] . Furthermore, a discrete exact approximation (i.e. a dotted representation) of the continuous efficient frontier can be found using quadratic programming algorithms which are included in many commercial software packages [5] . However, quadratic programmi...

show abstract

Particle swarm optimization approach to portfolio optimization

Cited by 226 publications

References 13 publications

Constrained Portfolio Optimisation: The State-of-the-Art Markowitz Models

Constrained Portfolio Optimisation: The State-of-the-Art Markowitz Models

Portfolio Optimization Using Particle Swarm Optimization And Genetic Algorithm

Portfolio Optimization with Metaheuristics

Contact Info

Product

Resources

About