A Comprehensive Analysis of Clustering Methods for Portfolio Optimization
Keywords:
Clustering Techniques; Machine Learning; Portfolio Optimization; Fundamental Analysis; Indian Financial Markets. JEL Classification codes: C38, C53, G11; G17Abstract
This paper presents a comprehensive exploratory analysis of financial performance of Indian companies, employing diverse clustering techniques and visualization methods. Core financial metrics, including Net Profit Margin (%), Earnings Per Share (EPS) Growth Rate (%), and Book Value (BV) Growth Rate (%), are examined over a decade. The study investigates optimal cluster numbers through Silhouette analysis and the Elbow Curve method, harnessing the power of unsupervised Machine Learning (ML). Employing K-Means and hierarchical clustering with various linkage strategies (single, complete, average, centroid, and ward), the research unveils insightful clustering structures through dendrogram visualizations. This analysis involves 50 undervalued companies, scrutinizing their financial dynamics and clustering profiles. The ensuing impact of indicators on trading activities and returns over both short and long time horizons (365 days and 10 years, respectively) is meticulously dissected. In particular, this study contrasts trade counts, total returns, and average return per trade vis-à-vis a benchmark of Nifty50 companies. The research findings substantiate that a majority of the clusters yield higher returns compared to Nifty50 counterparts for identical technical indicator combinations. The application of advanced ML methodologies in this research provides actionable insights from complex financial data, catering to the needs of both researchers and practitioners. Ultimately, this work enriches financial analysis and offers valuable inputs for refining trading strategies.
Downloads
References
J. Li, X. Wang, S. Ahmad, X. Huang, and Yousaf Ali Khan, “Optimization of investment strategies through machine learning.,” Heliyon, vol. 9, no. 5, pp. e16155–e16155, May 2023, doi: https://doi.org/10.1016/j.heliyon.2023.e16155.
M. Leippold, Q. Wang, and W. Zhou, “Machine-Learning in the Chinese Factor Zoo,” SSRN Electronic Journal, 2020, doi: https://doi.org/10.2139/ssrn.3754339.
V. Azevedo and C. Hoegner, “Enhancing stock market anomalies with machine learning,” Review of Quantitative Finance and Accounting, vol. 60, no. 8, Aug. 2022, doi: https://doi.org/10.1007/s11156-022-01099-z.
K. Ray, “Artificial Intelligence and Value Investing,” The Journal of Investing, vol. 27, no. 1, pp. 21–30, Feb. 2018, doi: https://doi.org/10.3905/joi.2018.27.1.021.
R. Chopra and G. D. Sharma, “Application of Artificial Intelligence in Stock Market Forecasting: A Critique, Review, and Research Agenda,” Journal of Risk and Financial Management, vol. 14, no. 11, p. 526, Nov. 2021, doi: https://doi.org/10.3390/jrfm14110526.
L. Chen, M. Pelger, and J. Zhu, “Deep Learning in Asset Pricing,” Management Science, vol. 12, no. 10, Feb. 2023, doi: https://doi.org/10.1287/mnsc.2023.4695.
F. Ren, Y.-N. Lu, S.-P. Li, X.-F. Jiang, L.-X. Zhong, and T. Qiu, “Dynamic Portfolio Strategy Using Clustering Approach,” PLOS ONE, vol. 12, no. 1, p. e0169299, Jan. 2017, doi: https://doi.org/10.1371/journal.pone.0169299.
T. Liu, “Non-Negative Matrix Factorization for Stock Market Pricing,” International Conference on Engineering and Informatics, Jan. 2009, doi: https://doi.org/10.1109/bmei.2009.5304773.
K. Marvin and S. Bhatt, “Creating Diversified Portfolios Using Cluster Analysis,” 2015. Available: https://www.cs.princeton.edu/sites/default/files/uploads/karina_marvin.pdf
M. Nourahmadi and H. Sadeqi, “Portfolio Diversification Based on Clustering Analysis,” Iranian Journal of Accounting, Auditing and Finance, vol. 7, no. 3, pp. 1–16, Aug. 2023, doi: https://doi.org/10.22067/ijaaf.2023.43078.1092.
J. Kim, Yae Jean Kim, S. Jung, Jong Ho Moon, and J. Kwon, “The effects of cluster collaboration and the utilization of big data on business performance: A research based on the expansion of open innovation and social capital,” African Journal of Science, Technology, Innovation and Development, vol. 14, no. 4, pp. 1032–1049, Jun. 2021, doi: https://doi.org/10.1080/20421338.2021.1925394.
Ahmad Zaman Khan and Mukesh Kumar Mehlawat, “Dynamic portfolio optimization using technical analysis‐based clustering,” International Journal of Intelligent Systems, vol. 37, no. 10, pp. 6978–7057, Mar. 2022, doi: https://doi.org/10.1002/int.22870.
S. R. Nanda, B. Mahanty, and M. K. Tiwari, “Clustering Indian stock market data for portfolio management,” Expert Systems with Applications, vol. 37, no. 12, pp. 8793–8798, Dec. 2010, doi: https://doi.org/10.1016/j.eswa.2010.06.026.
A. Cirulli, M. Kobak, and U. Ulrych, “Portfolio Construction with Hierarchical Momentum,” SSRN Electronic Journal, vol. 6, no. 1, 2022, doi: https://doi.org/10.2139/ssrn.4125072.
S. Roy, R. Bhattacharya, F. Advisor, and H. Khajar Bashir, “Identifying Homogeneity of Small-Cap Stocks in Indian Market: A Data Mining Approach,” Apr. 2019.
G. S. KONSTANTINOV and F. J. FABOZZI, “PORTFOLIO VOLATILITY SPILLOVER,” International Journal of Theoretical and Applied Finance, vol. 25, no. 04n05, Jun. 2022, doi: https://doi.org/10.1142/s0219024922500194.
Y. Wang and T. Aste, “Dynamic portfolio optimization with inverse covariance clustering,” Expert Systems With Applications, vol. 213, no. 1, pp. 118739–118739, Mar. 2023, doi: https://doi.org/10.1016/j.eswa.2022.118739.
E. J. Menvouta, S. Serneels, and T. Verdonck, “Portfolio optimization using cellwise robust association measures and clustering methods with application to highly volatile markets,” The Journal of Finance and Data Science, vol. 9, no. 6, p. 100097, Nov. 2023, doi: https://doi.org/10.1016/j.jfds.2023.100097.
T. Lim and C. Sin Ong, “Portfolio Diversification Using Shape-Based Clustering,” The Journal of Financial Data Science, vol. 3, no. 1, pp. 111–126, Dec. 2020, doi: https://doi.org/10.3905/jfds.2020.1.054.
O. Alqaryouti, Tarek Farouk, and Nur Siyam, “Clustering Stock Markets for Balanced Portfolio Construction,” Advanced Intelligent Systems and Informatics, vol. 53, no. 1, pp. 577–587, Sep. 2018, doi: https://doi.org/10.1007/978-3-319-99010-1_53.
S. Goudarzi, M. Jafari, and A. Afsar, “International Journal of Economics and Financial Issues A Hybrid Model for Portfolio Optimization Based on Stock Clustering and Different Investment Strategies,” International Journal of Economics and Financial Issues, vol. 7, no. 3, pp. 602–608, 2017.
S. Roy and R. Bhattacharya, “Clustering Mid-Cap Stocks in Indian Market using Multi-Variate Data Analysis Technique,” Indian Journal of Economics and Development, vol. 7, no. 6, pp. 1–10, Jun. 2019.
S. Burney, H. Tariq, and T. Jilani, “A Portfolio Optimization Algorithm Using Fuzzy Granularity Based Clustering AND BIOTECHNOLOGY View project ICT e-Helath View project,” 2019.
K. S. Pritam, T. Mathur, S. Agarwal, S. K. Paul, and A. Mulla, “A novel methodology for perception-based portfolio management,” Annals of Operations Research, vol. 315, no. 2, pp. 1107–1133, Feb. 2022, doi: https://doi.org/10.1007/s10479-022-04530-9.
A. M. Harsha and V. V. S. K. Rao, “Addressing Challenges in Stock Selection: A Financial Decision Support System Approach,” Journal of Research Administration, vol. 5, no. 2, pp. 4497–4510, Nov. 2023, [Online]. Available: https://journalra.org/index.php/jra/article/view/602
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
