optimal portfolio prediction in tehran stock market using multi-objective evolutionary algorithms, nsga-ii and mopso

Authors

مهسا رجبی

دانشجوی دکتری برق ـ کنترل و سیستم، دانشگاه صنعتی خواجه نصیرالدین طوسی، تهران، ایران حمید خالوزاده

استاد دانشگاه صنعتی خواجه نصیرالدین طوسی، تهران، ایران

abstract

despite the growing use of evolutionary multi-objective optimization algorithms in different categories of science, these algorithms as a powerful tool in portfolio optimization and specially solving multi-objective portfolio optimization problem is still in its early stages. in this paper, moeas have been used for solving multi-objective portfolio optimization problem in tehran stock market. for this purpose, non-dominated sorting genetic algorithm (nsga_ii) and multi-objective particle swarm optimization (mopso), as two common approaches, were compared with each other. using pareto front, investors can choose optimal portfolio based on different risks and returns. two objectives of the problem are return and risk of portfolio and cvar is the risk metric. in order to solve the problem, three real-world constraints were considered. the results indicate that these approaches have a high performance in constraint portfolio optimization.

Upgrade to premium to download articles

Sign up to access the full text

Already have an account?login

similar resources

using multi-objective algorithm (nsga-ii) in selecting optimal portfolio in tehran stock exchange

in financial matters, portfolio can be interpreted as a combination or a series of investments hold by an institution or a person. portfolio optimization is one of the most important concerns of investors for maximizing the portfolio in financial markets. the formation of portfolio is a vital and critical decision for the companies.  in fact, the selection of portfolio is to specify the capital...

full text

Determining the Optimal Stock Portfolio in Tehran Stock Exchange Based on Multi- Objective Evolutionary Algorithm with Error Level ( -MOEA)

Classical statistical models can solve the problem of portfolio optimization and can determine the efficient frontier of investment when there are few investable assets and constraints. But these models cannot easily solve optimization problems when we consider real-world constraints. Therefore, data mining techniques such as evolutionary algorithms are important in portfolio optimization. The ...

full text

Multi-Objective Evolutionary Algorithm NSGA-II for Protein Structure Prediction using Structural and Energetic Properties

The Protein Structure Prediction (PSP) problem is concerned about the prediction of the native tertiary structure of a protein in respect to its amino acids sequence. PSP is a challenging and computationally open problem. Therefore, several researches and methodologies have been developed for it. In this way, developers are working to integrate frameworks in order to improve their capabilities ...

full text

Using Genetic Algorithm in Solving Stochastic Programming for Multi-Objective Portfolio Selection in Tehran Stock Exchange

Investor decision making has always been affected by two factors: risk and returns. Considering risk, the investor expects an acceptable return on the investment decision horizon. Accordingly, defining goals and constraints for each investor can have unique prioritization. This paper develops several approaches to multi criteria portfolio optimization. The maximization of stock returns, the pow...

full text

MULTI-OBJECTIVE OPTIMAL DESIGN OF SATMD INCLUDING SOIL-STRUCTURE INTERACTION USING NSGA-II

In this paper, a procedure has been introduced to the multi-objective optimal design of semi-active tuned mass dampers (SATMDs) with variable stiffness for nonlinear structures considering soil-structure interaction under multiple earthquakes. Three bi-objective optimization problems have been defined by considering the mean of maximum inter-story drift as safety criterion of structural compone...

full text

Optimizing a multi-product closed-loop supply chain using NSGA-II, MOSA, and MOPSO meta-heuristic algorithms

This study aims to discuss the solution methodology for a closed-loop supply chain (CLSC) network that includes the collection of used products as well as distribution of the new products. This supply chain is presented on behalf of the problems that can be solved by the proposed meta-heuristic algorithms. A mathematical model is designed for a CLSC that involves three objective functions of ma...

full text

Hosted on Doprax cloud platform doprax.com

copyright © 2015-2023