Advanced search
2 files | 6.17 MB Add to list

A network-based strategy of price correlations for optimal cryptocurrency portfolios

Ruixue Jing (UGent) and Luis E C Rocha (UGent)
Author
Organization
Abstract
A cryptocurrency is a digital asset maintained by a decentralised system using cryptography. The complex correlations between the cryptocurrencies’ prices may be exploited to understand the market dynamics and build efficient investment portfolios. We use network methods to select cryptocurrencies and the Markowitz Portfolio Theory to create portfolios that are agnostic to future market behaviour. The performance of our network-based portfolios is optimal with 46 cryptocurrencies and superior to benchmarks for short-term investments, reaching up to 1, 066% average expected returns within 1 day. Cryptocurrency portfolio investment may be competitive but calls for caution given the high variability of prices.
Keywords
Cryptocurrency, Network model, Portfolio, Optimisation, Price correlation, Financial market, complexity, networks, econophysics, complex systems, DIVERSIFICATION, LSTM

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.15 MB
  • A network based strategy of price correlations for optimal cryptocurrency portfolios.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 5.02 MB

Citation

Please use this url to cite or link to this publication:

MLA
Jing, Ruixue, and Luis E. C. Rocha. “A Network-Based Strategy of Price Correlations for Optimal Cryptocurrency Portfolios.” FINANCE RESEARCH LETTERS, vol. 58, no. Part C, 2023, doi:10.1016/j.frl.2023.104503.
APA
Jing, R., & Rocha, L. E. C. (2023). A network-based strategy of price correlations for optimal cryptocurrency portfolios. FINANCE RESEARCH LETTERS, 58(Part C). https://doi.org/10.1016/j.frl.2023.104503
Chicago author-date
Jing, Ruixue, and Luis E C Rocha. 2023. “A Network-Based Strategy of Price Correlations for Optimal Cryptocurrency Portfolios.” FINANCE RESEARCH LETTERS 58 (Part C). https://doi.org/10.1016/j.frl.2023.104503.
Chicago author-date (all authors)
Jing, Ruixue, and Luis E C Rocha. 2023. “A Network-Based Strategy of Price Correlations for Optimal Cryptocurrency Portfolios.” FINANCE RESEARCH LETTERS 58 (Part C). doi:10.1016/j.frl.2023.104503.
Vancouver
1.
Jing R, Rocha LEC. A network-based strategy of price correlations for optimal cryptocurrency portfolios. FINANCE RESEARCH LETTERS. 2023;58(Part C).
IEEE
[1]
R. Jing and L. E. C. Rocha, “A network-based strategy of price correlations for optimal cryptocurrency portfolios,” FINANCE RESEARCH LETTERS, vol. 58, no. Part C, 2023.
@article{01HCWZ7WF8G8A3XS4N8DV2PKSJ,
  abstract     = {{A cryptocurrency is a digital asset maintained by a decentralised system using cryptography. The complex correlations between the cryptocurrencies’ prices may be exploited to understand the market dynamics and build efficient investment portfolios. We use network methods to select cryptocurrencies and the Markowitz Portfolio Theory to create portfolios that are agnostic to future market behaviour. The performance of our network-based portfolios is optimal with 46 cryptocurrencies and superior to benchmarks for short-term investments, reaching up to 1, 066% average expected returns within 1 day. Cryptocurrency portfolio investment may be competitive
but calls for caution given the high variability of prices.}},
  articleno    = {{104503}},
  author       = {{Jing, Ruixue and Rocha, Luis E C}},
  issn         = {{1544-6123}},
  journal      = {{FINANCE RESEARCH LETTERS}},
  keywords     = {{Cryptocurrency,Network model,Portfolio,Optimisation,Price correlation,Financial market,complexity,networks,econophysics,complex systems,DIVERSIFICATION,LSTM}},
  language     = {{eng}},
  number       = {{Part C}},
  pages        = {{8}},
  title        = {{A network-based strategy of price correlations for optimal cryptocurrency portfolios}},
  url          = {{http://doi.org/10.1016/j.frl.2023.104503}},
  volume       = {{58}},
  year         = {{2023}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: