Foundations and Trends® in Optimization > Vol 3 > Issue 3

Optimization Methods for Financial Index Tracking: From Theory to Practice

Konstantinos Benidis, The Hong Kong University of Science and Technology, Hong Kong, kbenidis@connect.ust.hk Yiyong Feng, The Hong Kong University of Science and Technology, Hong Kong, yiyong@connect.ust.hk Daniel P. Palomar, The Hong Kong University of Science and Technology, Hong Kong, palomar@ust.hk
 
Suggested Citation
Konstantinos Benidis, Yiyong Feng and Daniel P. Palomar (2018), "Optimization Methods for Financial Index Tracking: From Theory to Practice", Foundations and TrendsĀ® in Optimization: Vol. 3: No. 3, pp 171-279. http://dx.doi.org/10.1561/2400000021

Publication Date: 07 Jun 2018
© 2018 K. Benidis, Y. Feng and D. P. Palomar
 
Subjects
Optimization,  Robustness,  Design and analysis of algorithms,  Data mining,  Adaptive signal processing,  Multidimensional signal processing,  Sparse representations,  Statistical signal processing: Estimation and regression,  Mathematical Finance and Insurance,  Risk Analysis
 

Free Preview:

Download extract

Share

Download article
In this article:
1. What this monograph is about
2. Challenges in Index Tracking
3. Sparse Portfolios
4. Optimization Algorithms
5. Numerical Experiments
6. Conclusions
Abbreviations
Notation
Acknowledgements
References

Abstract

Index tracking is a very popular passive investment strategy. Since an index cannot be traded directly, index tracking refers to the process of creating a portfolio that approximates its performance. A straightforward way to do that is to purchase all the assets that compose an index in appropriate quantities. However, to simplify the execution, avoid small and illiquid positions, and large transaction costs, it is desired that the tracking portfolio consists of a small number of assets, i.e., we wish to create a sparse portfolio. Although index tracking is driven from the financial industry, it is in fact a pure signal processing problem: a regression of the financial historical data subject to some portfolio constraints with some caveats and particularities. Furthermore, the sparse index tracking problem is similar to many sparsity formulations in the signal processing area in the sense that it is a regression problem with some sparsity requirements. In its original form, sparse index tracking can be formulated as a combinatorial optimization problem. A commonly used approach is to use mixed-integer programming (MIP) to solve small sized problems. Nevertheless, MIP solvers are not applicable for high-dimensional problems since the running time can be prohibiting for practical use. The goal of this monograph is to provide an in-depth overview of the index tracking problem and analyze all the caveats and practical issues an investor might have, such as the frequent rebalancing of weights, the changes in the index composition, the transaction costs, etc. Furthermore, a unified framework for a large variety of sparse index tracking formulations is provided. The derived algorithms are very attractive for practical use since they provide efficient tracking portfolios orders of magnitude faster than MIP solvers.

DOI:10.1561/2400000021
ISBN: 978-1-68083-464-2
122 pp. $85.00
Buy book (pb)
 
ISBN: 978-1-68083-465-9
122 pp. $140.00
Buy E-book (.pdf)
Table of contents:
1. What this monograph is about
2. Challenges in Index Tracking
3. Sparse Portfolios
4. Optimization Algorithms
5. Numerical Experiments
6. Conclusions
Abbreviations
Notation
Acknowledgements
References

Optimization Methods for Financial Index Tracking: From Theory to Practice

Index tracking is a very popular passive investment strategy. Since an index cannot be traded directly, index tracking refers to the process of creating a portfolio that approximates its performance. A straightforward way to do that is to purchase all the assets that compose an index in appropriate quantities. However, to simplify the execution, avoid small and illiquid positions and large transaction costs, it is desired that the tracking portfolio consists of a small number of assets.

Although index tracking is driven from the financial industry, it is in fact a pure signal processing problem: a regression of the financial historical data subject to some portfolio constraints with some caveats and particularities. Furthermore, the sparse index tracking problem is similar to many sparsity formulations in the signal processing area in the sense that it is a regression problem with some sparsity requirements. In its original form, sparse index tracking can be formulated as a combinatorial optimization problem. A commonly used approach is to use mixed-integer programming (MIP) to solve small sized problems. Nevertheless, MIP solvers are not applicable for high-dimensional problems since the running time can be prohibiting for practical use.

This monograph provides an in-depth overview of the index tracking problem and analyzes all the caveats and practical issues an investor might have. Furthermore, it provides a unified framework for a large variety of sparse index tracking formulations. The derived algorithms are very attractive for practical use since they provide efficient tracking portfolios orders of magnitude faster than MIP solvers.

 
OPT-021