Clustering Stock Markets for Balanced Portfolio Construction

被引：3

作者：

Alqaryouti, Omar ^{[1
]}

Farouk, Tarek ^{[1
]}

Siyam, Nur ^{[1
]}

机构：

[1] British Univ Dubai, Dubai, U Arab Emirates

来源：

PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT SYSTEMS AND INFORMATICS 2018 | 2019年 / 845卷

关键词：

Data mining in stock markets; Clustering stock markets; Portfolio construction; Cluster performance evaluation; K-means; K-medoids;

D O I：

10.1007/978-3-319-99010-1_53

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Nowadays, in the diversifying economic environment, investors need various ways to help them in taking the right decisions and maximize their returns within certain acceptable risk. This research paper incorporates data mining clustering techniques to assist investors in constructing a balanced portfolio in Abu Dhabi Securities Exchange (ADX). The study examines and analyses ADX trade market history for the year of 2015. An extensive analysis has been done for various combinations of pre-processing-clustering algorithm techniques. An unexpected conclusion was revealed from this research. It is believed that small markets such as Abu Dhabi's require different "clustering" treatment than the commonly applied ones for established markets such as New York Stock Exchange.

引用

页码：577 / 587

页数：11