Metaheuristics for Portfolio Optimization

An Introduction using MATLAB®

Volume 11 – Metaheuristics SET Coordinated by Nicolas Monmarché and Patrick Siarry

Metaheuristics for Portfolio Optimization

G A Vijayalakshmi Pai, PSG College of Technology, Coimbatore, India

ISBN : 9781786302816

Publication Date : December 2017

Hardcover 316 pp

145.00 USD



In recent times, the problem of portfolio optimization has become increasingly complex due to the myriad objectives and constraints induced by the market norms, investor preferences and investment strategies which define the underlying portfolios. With the required mathematical models finding little help from traditional methods, there has been a growing need to look for non-traditional algorithms from the emerging field of Metaheuristics, a sub-discipline of Computational Intelligence, to arrive at the optimal portfolios.

This book therefore elucidates a collection of strategic portfolio optimization models, such as risk budgeting, market neutral investing and portfolio rebalancing, which employ metaheuristics for their effective solutions. The results are demonstrated using MATLAB® implementations on live portfolios invested across global stock universes. The MATLAB® programs and functions can be accessed at the MATLAB Central File Server.

This book, belonging to the cross-disciplinary field of Computational Intelligence in Finance, is structured to appeal to readers who are novices in finance or metaheuristics.


1. Introduction to Portfolio Optimization.
2. A Brief Primer on Metaheuristics.
3. Heuristic Portfolio Selection.
4. Metaheuristic Risk-Budgeted Portfolio Optimization.
5. Heuristic Optimization of Equity Market Neutral Portfolios.
6. Metaheuristic 130-30 Portfolio Construction.
7. Metaheuristic Portfolio Rebalancing with Transaction Costs.

About the authors

G A Vijayalakshmi Pai is Associate Professor of Computer Applications at PSG College of Technology, Coimbatore, India. She is a Senior Member of the IEEE and her research interests span the fields of Computational Intelligence, Computational Finance and Machine Learning.

Related subject