Adopting centrality measure models in visualized financial datasets

Jie Hua; Guohua Wang; Youquan Xu

doi:10.1117/12.2537801

27 November 2019 Adopting centrality measure models in visualized financial datasets

Jie Hua, Guohua Wang, Youquan Xu

Proceedings Volume 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence; 1132103 (2019) https://doi.org/10.1117/12.2537801
Event: The Second International Conference on Image, Video Processing and Artifical Intelligence, 2019, Shanghai, China

Abstract

The financial data is complex to analyse due to its complicated relationships and multiple attributes. Centrality measure models from the SNA (Social network analysis) can show the most critical variables in a network, and graph layouts can be produced to represent not only data networks but also the relations among data entries. To the best of our knowledge, there is no work that has been tried on the Australian stock market based on the combination of those two methods mentioned above so far. This study adopts centrality measure methods and a graph drawing algorithm (force-directed) to offer users big pictures and detailed views, comes with ranking factors based on weighted degree, pagerank and eigenvector metrics. The outcomes show that the methodology can produce clear graph layouts of the stock’s social network, identify the central stocks (represent through features such as node colour and size) and the business sectors they belong to. This study may assist stakeholders with grasping deep insight from the complex financial datasets, and another angle of view to adjust future investments accordingly.

Citation Download Citation

Jie Hua, Guohua Wang, and Youquan Xu "Adopting centrality measure models in visualized financial datasets", Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 1132103 (27 November 2019); https://doi.org/10.1117/12.2537801

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available