Projecting Financial Technical Indicators Into Networks as a Tool to Build a Portfolio

Dongxu Mo,Yan Chen

doi:10.1109/access.2021.3064924

Dongxu Mo, Yan Chen

Open Access

https://doi.org/10.1109/access.2021.3064924

Copy DOI

Abstract

Using the topological structure of financial networks to build a portfolio has attracted a wide range of research interests. A similarity matrix based on the technical indicators (TIs), and a correlation matrix based on the stock returns, are used to construct the financial networks. Hybrid topological measures are calculated for both networks to select the stocks that are further used to build portfolios. The random matrix theory (RMT) tool is used to filter the risk measurement in the Markowitz optimization process. A general result is presented in this study, which indicates that the portfolios composed of peripheral stocks consistently outperform those composed of central stocks. As shown in the empirical results, the RMT method can improve the Markowitz optimization process and further improve the performance of portfolios. By comparing the different portfolios established under different networks, the results reveal the advantage of the topological measure based on TIs. This study provides an important approach for constructing financial networks from the time series data, and it explores the impact of different similarity measurements on the network-based models for portfolio selection.

Highlights

As the most important research contribution in the field of portfolio selection, Markowitz [1] proposed a mean-variance model, in which a return is considered as the mean and a risk is considered as the variance
Consider a case of peripheral stocks, we select ten stocks with the top 1-10 hybrid topological measures, that is the case of m = 10, the overlapping probability is low; we select twenty stocks with the top 1-20 hybrid topological measures, that is the case of m = 20, the overlapping probability increases relative to the case of m = 10; it means that the increasing part of the overlapping probability derives from the contribution of the top 11-20 stocks
The most peripheral/central stocks selected from a correlation-based network and a similarity-based network are very different, further indicating that the performance of portfolios constructed by the selected stocks from the two networks would be different

Summary

Introduction

As the most important research contribution in the field of portfolio selection, Markowitz [1] proposed a mean-variance model, in which a return is considered as the mean and a risk is considered as the variance. In this framework, investors aim at allocating their wealth among a set of assets to maximize the expected return for a given level of risk. Researchers proposed many portfolio selection methods from different perspectives to improve the performance of portfolio optimization These studies can be roughly divided into three types. Liu and Zhang [2] introduced a lower semi-variance as risk

Objectives

Results

Conclusion