Swarm Intelligence in Finance: A Comparative Analysis of ACO and PSO for Mean–Variance Portfolio Optimization

Heena J Patel; Prashant P Pittalia

doi:10.71097/IJSAT.v16.i3.7161

Swarm Intelligence in Finance: A Comparative Analysis of ACO and PSO for Mean–Variance Portfolio Optimization

Author(s)	Heena J Patel, Dr. Prashant P Pittalia
Country	India
Abstract	Portfolio optimization poses a significant challenge for modern portfolio managers as they strive to balance expected returns against inherent risks. In the quest to create optimal portfolios, selecting the appropriate tools and techniques is paramount. One of the most widely adopted frameworks is the Markowitz mean–variance model, renowned for its effectiveness in addressing the portfolio selection problem. However, while the standard Markowitz formulation is NP-hard, the complexity escalates considerably when additional variables or constraints, such as cardinality restrictions, are introduced, transforming the problem into a nonlinear mixed integer programming challenge that is far more demanding to solve. Identifying the most effective algorithms for multi-objective portfolio optimization is a crucial task. Therefore, researchers need to identify the most appropriate algorithms. This research examines two prevalent swarm intelligence (SI) algorithms: Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO), for portfolio optimization. The study evaluates the performance of these optimization algorithms in addressing real-world constraints associated with portfolio construction. The performance and robustness of the portfolios are evaluated through anchored and unanchored cross-validation methods, using six years of daily trading data from 20 randomly selected stocks listed on the National Stock Exchange (NSE) of India. Descriptive statistics of this study show that the average Sharpe ratio of five test folds using the anchored cross-validation method is 0.53 for ACO and 0.61 for PSO. The unanchored cross-validation method produced an average Sharpe ratio of 0.90 for ACO and 0.87 for PSO in the five test folds. The detailed analysis of the experimental data set reveals that PSO outperforms ACO. Further, the return obtained from portfolios constructed by ACO and PSO outperforms the Nifty 100 Index returns.
Keywords	Ant Colony Optimization, Mean-Variance Model, Particle Swarm Optimization, Portfolio Asset Allocation, Swarm Intelligence
Field	Computer Applications
Published In	Volume 16, Issue 3, July-September 2025
Published On	2025-07-22
DOI	https://doi.org/10.71097/IJSAT.v16.i3.7161
Short DOI	https://doi.org/g9t2x3

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 16 Isu 3 Cover Page Vol 16 Isu 2 Cover Page Vol 16 Isu 1

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Swarm Intelligence in Finance: A Comparative Analysis of ACO and PSO for Mean–Variance Portfolio Optimization

Share this