Accounting and Auditing Research

Accounting and Auditing Research

Stock Market Analysis Using Complex Networks Approach

Document Type : Original Article

Authors
Leila Lotfi 1
Yahya Kamyabi 2
1 Ph.D. Candidate, Department of Accounting, University of Mazandaran, Babolsar, Iran
2 Professor, Department of Accounting, University of Mazandaran, Babolsar, Iran
10.22034/iaar.2025.236286
Abstract
Objective
In recent years, financial physics and complex network techniques have an outstanding role in financial and economic systems studies. Therefore, the present research aims to use the complex network method to analyze the stock market.
Methods
Studying the stock market data using the complex network approach is an interdisciplinary and quantitative research on the border of graph theory, financial physics, and economics. In this research, to build and investigate the complex networks of the stock market data of 618 companies during the years 1390 to 1400 in the form of 48 industries, Python software (Python 3) and existing libraries (Numpy, NetworkX, Scipy) were applied.
Results
In this study, we have investigated various parameters of the complex network. By examining the trend of degree centrality and closeness centrality, the changes of the network during critical years are clearly observed. The similarity of the networks was shown using the similarity parameter.
Conclusion
The results exhibit that the constructed have the characteristics of small world network. Over the years, the centrality has shifted between industries, which shows that networks are not stable over time. Both degree centrality and closeness centrality have their highest values during crisis years, which shows that the crisis has affected all industries and different economic sectors. The study of the similarity parameter showed that during the crisis years, the networks had the most similarity with each other and were quite dense.
Keywords
Complex Systems, Financial Complex Network, Graph Theory, Network Science, Stock Correlation
1.       تقی‌زاده، رضا و عبدزاده کنفی، محمد، (1402). "تحلیلی بر بازار سرمایه با استفاده از رویکرد شبکه". تحقیقـات مـالی، 25(3)، صص. 369-386.
2.       چهارسوقی، سیدکمال، و رحیم نژاد، فریده. (1395). کاربرد شبکه های پیچیده در تحلیل بازار سهام. کنفرانس ملی نوآوری در مدیریت سیستم ها و فناوری اطلاعات با رویکرد هوشمندی کسب و کار.
3.       سرچمی، محمد. خدامی‌پور، احمد. محمدی، مجید و حدیث، زینلی، (1402). "ارزیابی توان مدل یادگیری عمیق و مدل مارکوئیتز در تشکیل پرتفوی بهینه سهام". تحقیقات حسابداری و حسابرسی، انجمن حسابداری ایران، دوره 15، شماره 57، صص 47-68.
4.       صادقی، حجت‌اله، (1398). "فیزیک مالی به عنوان زمینه‌ای بین رشته‌ای؛ خدمات دانش فیزیک به مالی و نقد آنها". پژوهشنامه انتقادی متون و برنامه‌های علوم انسانی، 19(9 )، صص. 93-112.
5.       هاشمی گل سفیدی، افشین. لشگری، زهرا و زهره، حاجیها، (1401). "کاربرد یادگیری ماشین در ارائه الگویی برای پیش‌بینی ورشکستگی". تحقیقات حسابداری و حسابرسی، انجمن حسابداری ایران، دوره 14، شماره 56، صص 171-190.
6.       Bardoscia, M., Barucca, P., Battiston, S., Caccioli, F., Cimini, G., Garlaschelli, D., ... and Caldarelli, G. )2021(. “The physics of financial networks”. Nature Reviews Physics, 3(7), pp. 490-507.
7.       Battiston, S., et al. (2016). “Complexity theory and financial regulation”. Science, 351, pp. 818–819.
8.       Bhattacharya, S., Sinha, S., Dey, P., Saha, A., Chowdhury, C., and Roy, S. )2023(. Online social-network sensing models. Computational Intelligence Applications for Text and Sentiment Data Analysis, pp. 113-140. Academic Press.
9.       Coletti, P., Murgia, M. )2017(. “The network of the Italian stock market during the 2008–2011 financial crises”, Algorithmic Financ. (5), pp. 111–137.
10.   Dimitri, G. M. )2023(. “Is Facebook regionally a small world network?” arXiv preprint arXiv:2301.04916.
11.   Fontoura Costa, L. da. )2021(. “Further generalizations of the jaccard index”, ArXiv abs/2110.09619.
12.   Huang, W., Wang, H., Wei, Y., et al. )2024(. “Complex network analysis of global stock market co-movement during the COVID-19 pandemic based on intraday open-high-low-close data”. Financ Innov 10, 7.
13.   Humphries, M. D., Gurney, K. )2008(. “Network ‘small-world-ness’: a quantitative method for determining canonical network equivalence”, PLoS ONE 3 (4) e0002051.
14.   Jin, Y., Lin, CY., Matsuo, Y., et al. )2012(. “Mining dynamic social networks from public news articles for company value prediction”. Soc Netw Anal Min. 2(3), pp. 217–228.
15.   Li, B., Pi, D. )2018(. “Analysis of global stock index data during crisis period via complex network approach”. PLoS ONE 13(7): e0200600.
16.   Nobi, A., Lee, S., Kim, DH., et al. )2014(. “Correlation and network topologies in global and local stock indices”. Phys Lett A 378(34), pp. 2482–2489.
17.   Peng, SH., Han, W., Jia, G. )2022(. “Pearson correlation and transfer entropy in the Chinese stock market with time delay”, Data Science and Management, (5), Issue 3, pp. 117-123.
18.   Qiao, H., Xia, Y., Li, Y. )2016(. “Can network linkage effects determine return? evidence from Chinese stock market”, PLoS One 11 (6) e0156784.
19.   Schwartz, G. A. )2021(. “Complex networks reveal emergent interdisciplinary knowledge in Wikipedia”. Humanities and Social Sciences Communications, 8(1), pp. 1-6.
20.   Van Mieghem, P. )2023(. “Graph spectra for complex networks”. Cambridge university press.
21.   Yang, C., Chen, Y., Niu, L. and Li, Q. )2014(. “Cointegration analysis and influence rank-A network approach to global stock markets”. Physica A, 400, pp. 168–185.
Accounting and Auditing Research
Volume 17, Issue 67
Autumn 2025
Pages 67-84