Cardinality Constrained Portfolio Optimization on an Ising Machine

Matthieu Parizy; Przemyslaw Sadowski; Nozomu Togawa

doi:10.1109/SOCC56010.2022.9908082

Cardinality Constrained Portfolio Optimization on an Ising Machine

Matthieu Parizy, Przemyslaw Sadowski, Nozomu Togawa

School of Fundamental Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we propose an Ising-machine based method for solving the cardinality constrained mean-variance portfolio optimization problem (CCMVPOP), which is an NP-hard problem and often solved using metaheuristics. Firstly, we formulate this problem as a binary quadratic program (BQP) to be solved by an Ising machine-software system. Namely, we propose formulations for each objective and constraint using binary variables exclusively. Furthermore, we evaluate and compare well known integer to binary variable encoding as well as propose a new encoding for the CCMVPOP. The evaluation is done by studying which encoding converges the fastest to the highest return over risk collection of assets for a given data set which represent stocks involved in a capital market index. Used data range from capital market index composed of 31 assets for the smallest and up to 225 for the largest. The experimental results confirm that the proposed formulations to the CCMVPOP for an Ising machine-software system are effective.

Original language	English
Title of host publication	Proceedings - 2022 IEEE 35th International System-on-Chip Conference, SOCC 2022
Editors	Sakir Sezer, Thomas Buchner, Jurgen Becker, Andrew Marshall, Fahad Siddiqui, Tanja Harbaum, Kieran McLaughlin
Publisher	IEEE Computer Society
ISBN (Electronic)	9781665459853
DOIs	https://doi.org/10.1109/SOCC56010.2022.9908082
Publication status	Published - 2022
Event	35th IEEE International System-on-Chip Conference, SOCC 2022 - Belfast, Northern Ireland, United Kingdom Duration: 2022 Sept 5 → 2022 Sept 8

Publication series

Name	International System on Chip Conference
Volume	2022-September
ISSN (Print)	2164-1676
ISSN (Electronic)	2164-1706

Conference

Conference	35th IEEE International System-on-Chip Conference, SOCC 2022
Country/Territory	United Kingdom
City	Belfast, Northern Ireland
Period	22/9/5 → 22/9/8

Keywords

Ising machine
cardinality constraint
integer encoding
optimization
portfolio

ASJC Scopus subject areas

Hardware and Architecture
Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/SOCC56010.2022.9908082

Cite this

Parizy, M., Sadowski, P., & Togawa, N. (2022). Cardinality Constrained Portfolio Optimization on an Ising Machine. In S. Sezer, T. Buchner, J. Becker, A. Marshall, F. Siddiqui, T. Harbaum, & K. McLaughlin (Eds.), Proceedings - 2022 IEEE 35th International System-on-Chip Conference, SOCC 2022 (International System on Chip Conference; Vol. 2022-September). IEEE Computer Society. https://doi.org/10.1109/SOCC56010.2022.9908082

Cardinality Constrained Portfolio Optimization on an Ising Machine. / Parizy, Matthieu; Sadowski, Przemyslaw; Togawa, Nozomu.
Proceedings - 2022 IEEE 35th International System-on-Chip Conference, SOCC 2022. ed. / Sakir Sezer; Thomas Buchner; Jurgen Becker; Andrew Marshall; Fahad Siddiqui; Tanja Harbaum; Kieran McLaughlin. IEEE Computer Society, 2022. (International System on Chip Conference; Vol. 2022-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Parizy, M, Sadowski, P & Togawa, N 2022, Cardinality Constrained Portfolio Optimization on an Ising Machine. in S Sezer, T Buchner, J Becker, A Marshall, F Siddiqui, T Harbaum & K McLaughlin (eds), Proceedings - 2022 IEEE 35th International System-on-Chip Conference, SOCC 2022. International System on Chip Conference, vol. 2022-September, IEEE Computer Society, 35th IEEE International System-on-Chip Conference, SOCC 2022, Belfast, Northern Ireland, United Kingdom, 22/9/5. https://doi.org/10.1109/SOCC56010.2022.9908082

Parizy M, Sadowski P, Togawa N. Cardinality Constrained Portfolio Optimization on an Ising Machine. In Sezer S, Buchner T, Becker J, Marshall A, Siddiqui F, Harbaum T, McLaughlin K, editors, Proceedings - 2022 IEEE 35th International System-on-Chip Conference, SOCC 2022. IEEE Computer Society. 2022. (International System on Chip Conference). doi: 10.1109/SOCC56010.2022.9908082

Parizy, Matthieu ; Sadowski, Przemyslaw ; Togawa, Nozomu. / Cardinality Constrained Portfolio Optimization on an Ising Machine. Proceedings - 2022 IEEE 35th International System-on-Chip Conference, SOCC 2022. editor / Sakir Sezer ; Thomas Buchner ; Jurgen Becker ; Andrew Marshall ; Fahad Siddiqui ; Tanja Harbaum ; Kieran McLaughlin. IEEE Computer Society, 2022. (International System on Chip Conference).

@inproceedings{2506b7f33bd6446f9771c8fe62388403,

title = "Cardinality Constrained Portfolio Optimization on an Ising Machine",

abstract = "In this paper, we propose an Ising-machine based method for solving the cardinality constrained mean-variance portfolio optimization problem (CCMVPOP), which is an NP-hard problem and often solved using metaheuristics. Firstly, we formulate this problem as a binary quadratic program (BQP) to be solved by an Ising machine-software system. Namely, we propose formulations for each objective and constraint using binary variables exclusively. Furthermore, we evaluate and compare well known integer to binary variable encoding as well as propose a new encoding for the CCMVPOP. The evaluation is done by studying which encoding converges the fastest to the highest return over risk collection of assets for a given data set which represent stocks involved in a capital market index. Used data range from capital market index composed of 31 assets for the smallest and up to 225 for the largest. The experimental results confirm that the proposed formulations to the CCMVPOP for an Ising machine-software system are effective.",

keywords = "Ising machine, cardinality constraint, integer encoding, optimization, portfolio",

author = "Matthieu Parizy and Przemyslaw Sadowski and Nozomu Togawa",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 35th IEEE International System-on-Chip Conference, SOCC 2022 ; Conference date: 05-09-2022 Through 08-09-2022",

year = "2022",

doi = "10.1109/SOCC56010.2022.9908082",

language = "English",

series = "International System on Chip Conference",

publisher = "IEEE Computer Society",

editor = "Sakir Sezer and Thomas Buchner and Jurgen Becker and Andrew Marshall and Fahad Siddiqui and Tanja Harbaum and Kieran McLaughlin",

booktitle = "Proceedings - 2022 IEEE 35th International System-on-Chip Conference, SOCC 2022",

}

TY - GEN

T1 - Cardinality Constrained Portfolio Optimization on an Ising Machine

AU - Parizy, Matthieu

AU - Sadowski, Przemyslaw

AU - Togawa, Nozomu

PY - 2022

Y1 - 2022

N2 - In this paper, we propose an Ising-machine based method for solving the cardinality constrained mean-variance portfolio optimization problem (CCMVPOP), which is an NP-hard problem and often solved using metaheuristics. Firstly, we formulate this problem as a binary quadratic program (BQP) to be solved by an Ising machine-software system. Namely, we propose formulations for each objective and constraint using binary variables exclusively. Furthermore, we evaluate and compare well known integer to binary variable encoding as well as propose a new encoding for the CCMVPOP. The evaluation is done by studying which encoding converges the fastest to the highest return over risk collection of assets for a given data set which represent stocks involved in a capital market index. Used data range from capital market index composed of 31 assets for the smallest and up to 225 for the largest. The experimental results confirm that the proposed formulations to the CCMVPOP for an Ising machine-software system are effective.

AB - In this paper, we propose an Ising-machine based method for solving the cardinality constrained mean-variance portfolio optimization problem (CCMVPOP), which is an NP-hard problem and often solved using metaheuristics. Firstly, we formulate this problem as a binary quadratic program (BQP) to be solved by an Ising machine-software system. Namely, we propose formulations for each objective and constraint using binary variables exclusively. Furthermore, we evaluate and compare well known integer to binary variable encoding as well as propose a new encoding for the CCMVPOP. The evaluation is done by studying which encoding converges the fastest to the highest return over risk collection of assets for a given data set which represent stocks involved in a capital market index. Used data range from capital market index composed of 31 assets for the smallest and up to 225 for the largest. The experimental results confirm that the proposed formulations to the CCMVPOP for an Ising machine-software system are effective.

KW - Ising machine

KW - cardinality constraint

KW - integer encoding

KW - optimization

KW - portfolio

UR - http://www.scopus.com/inward/record.url?scp=85140752466&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85140752466&partnerID=8YFLogxK

U2 - 10.1109/SOCC56010.2022.9908082

DO - 10.1109/SOCC56010.2022.9908082

M3 - Conference contribution

AN - SCOPUS:85140752466

T3 - International System on Chip Conference

BT - Proceedings - 2022 IEEE 35th International System-on-Chip Conference, SOCC 2022

A2 - Sezer, Sakir

A2 - Buchner, Thomas

A2 - Becker, Jurgen

A2 - Marshall, Andrew

A2 - Siddiqui, Fahad

A2 - Harbaum, Tanja

A2 - McLaughlin, Kieran

PB - IEEE Computer Society

T2 - 35th IEEE International System-on-Chip Conference, SOCC 2022

Y2 - 5 September 2022 through 8 September 2022

ER -

Cardinality Constrained Portfolio Optimization on an Ising Machine

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this