A simple parallel algorithm for large-scale portfolio problems

Purpose - Although the mean-variance portfolio selection model has been investigated in the literature, the difficulty associated with the application of the model when dealing with large-scale problems is limited. The aim of this paper is to close the gap by using the quadratic risk (standard devia...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The journal of risk finance Jg. 11; H. 5; S. 481 - 495
Hauptverfasser: Smimou, Kamal, Thulasiram, Ruppa K
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Emerald Group Publishing Limited 09.11.2010
Emerald
Emerald Group Publishing, Ltd
Schlagworte:
ISSN:1526-5943, 2331-2947
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Purpose - Although the mean-variance portfolio selection model has been investigated in the literature, the difficulty associated with the application of the model when dealing with large-scale problems is limited. The aim of this paper is to close the gap by using the quadratic risk (standard deviation risk) function and finite iteration technique to remove difficulties in quadratic programming.Design methodology approach - Using van de Panne' approach, this paper proposes a finite technique to optimize large-scale portfolio selection problem.Findings - The proposal of parallel algorithm structure to the model provides a clearer decision framework to significantly enhance the efficiency of the portfolio selection process.Originality value - The proposal of parallel algorithm structure to the mean-variance portfolio selection model provides a clearer decision framework to significantly enhance the efficiency of the portfolio selection process. An empirical example that illustrates the application and benefits of the method is provided.
Bibliographie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:1526-5943
2331-2947
DOI:10.1108/15265941011092068