An Analysis of Centrality’s Features as a New Measure for Network Analysis, Risk Measurement & Portfolio Selection

Abstract

Objective: In network theory, centrality is a measure to estimate importance and influence of a special node to the whole network structure. The aim of this research is to investigate the characteristics of stock centrality and its reliability in risk estimation and portfolio selection. Methods: First in this paper, we analyzed the relationship between stock’s centrality & benchmark risk estimation measures like beta & standard deviation. Then, we analyzed the relationship between stock’s centrality & Markowitz framework’s weights; and finally, we introduced centrality-based portfolio selection strategy and compared it with other benchmarks, by different portfolio performance measures. Results: Our observations indicate that in Tehran stock exchange, centrality can have an effective role in stocks risk estimation and there is a meaningful relation between centrality and other measures. We also observed that out that low central stocks can raise the benefits of portfolio diversification, and centrality-based portfolio selection method can have a better performance than other benchmark portfolio selection methods and results in a better risk adjusted return. Conclusion: Stock centrality, as a measure to estimate importance and influence of member of a network, is capable of describing stock risk characteristics like other accepted measures. We can take advantage of this capability for portfolio selection.

Keywords

• : centrality
• centrality based strategy
• financial market network
• portfolio selection