Portfolio Optimisation in the Cryptocurrency Market: Hybrid Integration of Markowitz and Ridge Methods

Basit Öğe Kaydı
dc.contributor.authorYildirim, Ruya Kaplan
dc.contributor.authorMunyas, Turgay
dc.contributor.authorAydin, Gulden Kadooglu
dc.date.accessioned2026-02-27T07:33:16Z
dc.date.available2026-02-27T07:33:16Z
dc.date.issued2025
dc.description.abstractConstructing an effective asset allocation strategy requires buildingwell-diversified portfolios that maintain robust performance beyond the sample data. The classical Markowitz portfolio optimisation, while widely used, is known to suffer from issues such as estimation errors and sensitivity to multicollinearity, which can significantly distort the allocation process and reduce performance reliability. In order to surmount the aforementioned challenges, the incorporation of Machine Learning echniques, specifically Ridge regression, into the portfolio creation process has been effected. This has resulted in the provision of a hybrid model that combines the strengths of Markowitz optimisation and Ridge regression. The integration of these approaches within the hybrid model serves to mitigate the prediction risks while maintaining the diversification benefits inherent to the Markowitz framework. The model was trained using an 80/20 split and cross-validation was employed to prevent overfitting. The findings indicate that this integrated approach attains the maximum Sharpe ratio, thereby significantly enhancing risk-adjusted returns and portfolio stability when applied to cryptoasset returns. The findings emphasise the merits of integrating classical optimisation methodologies with machine learning to develop more robust and adaptive asset allocation strategies. By analysing the impact of high-volatility cryptoassets on portfolio performance, it makes important contributions to both the literature and practical portfolio strategies for investors.
dc.identifier.doi10.26650/ISTJECON2024-1643134
dc.identifier.endpage221
dc.identifier.issn2602-4152
dc.identifier.issn2602-3954
dc.identifier.issue1
dc.identifier.startpage207
dc.identifier.urihttp://dx.doi.org/10.26650/ISTJECON2024-1643134
dc.identifier.urihttps://hdl.handle.net/20.500.14669/4525
dc.identifier.volume75
dc.identifier.wosWOS:001538157000012
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakTR-Dizin
dc.language.isoen
dc.publisherİstanbul Univ
dc.relation.ispartofİstanbul İktisat Dergisi-İstanbul Journal of Economics
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_20260302
dc.subjectHybrid method
dc.subjectCrypto assets
dc.subjectMarkowitz optimisation
dc.subjectRidge method
dc.titlePortfolio Optimisation in the Cryptocurrency Market: Hybrid Integration of Markowitz and Ridge Methods
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
TR-Dizin İndeksli Yayınlar Koleksiyonu