PORTFOLIO OPTIMIZATION USING PCA CLASSIFICATION AND GENETICS ALGORITHM

Naceur Rahmani and Khelil Naceur
Additional contact information
Naceur Rahmani: Laboratory of Applied Mathematics. University of Biskra. PO Box 145 RP 07000 BISKRA, Algeria.
Khelil Naceur: Laboratory of Applied Mathematics. University of Biskra. PO Box 145 RP 07000 BISKRA, Algeria.

Post-Print from HAL

Abstract: Portfolio optimization is one of the main investors in financial markets, we present in this paper a new approach to obtain an optimal portfolio, which minimizes the risk for a required profit or maximizing the profit of a given risk. To solve the problem we first introduce a concept of mean absolute deviation risk (MAD). The MAD L1risk function can remove most difficulties associated with the Markowitz's model. We use heuristic evolutionary algorithm to find the optimal portfolio. We have proposed an approach to find a feasible shares portfolio invested in market based on MAD by using PCA (principal component analysis) and genetic algorithm (GA). This approach is organized in two steps: the first one is to use the PCA classification method to classify the actions into classes. In second step we use an algorithm of optimization called MAD-PAG based on genetic algorithm and mean absolute deviation to minimize the risk measured by the MAD and maximize the value of portfolio.

Date: 2019-04-29
References: Add references at CitEc
Citations:

Published in Journal of Global Economics, Management and Business Research, 2019, 11 (3), pp.129-141

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-05306016

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().