arbiter
JournalsPricingAccount

Integrating Choquet portfolios and machine learning interpretability for robust cryptocurrency investment strategies

João Pedro M. Franco & Márcio P. Laurini

The Journal of Finance and Data Science2025https://doi.org/10.1016/j.jfds.2025.100172article
ABDC B
Weight
0.50

What the paper says

This study proposes an alternative approach to portfolio optimization in the cryptocurrency market by applying the Choquet integral portfolio, positioning it within the broader context of Robo-Advisor literature. This approach is based on pessimistic decision-making and employs higher order moments and captures asset interdependencies, thereby offering a notable advantage over traditional portfolio construction methods, including mean-variance optimization, naive diversification, and a Bitcoin-only portfolio. Furthermore, our study applies Machine Learning Interpretable Methods (Shapley and LIME) to identify the cryptocurrencies that drive portfolio returns over time. The findings highlight the significance of integrating interpretable machine learning tools with advanced portfolio models to furnish more profound insights into the determinants of portfolio performance, which consequently facilitates more informed and transparent investment decisions. Moreover, our findings aid investors in comprehending the methodology by which these automated processes allocate weights according to a portfolio model within the highly volatile cryptocurrency market.

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.1016/j.jfds.2025.100172

Or copy a formatted citation

@article{joão2025,
  title        = {{Integrating Choquet portfolios and machine learning interpretability for robust cryptocurrency investment strategies}},
  author       = {João Pedro M. Franco & Márcio P. Laurini},
  journal      = {The Journal of Finance and Data Science},
  year         = {2025},
  doi          = {https://doi.org/https://doi.org/10.1016/j.jfds.2025.100172},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Integrating Choquet portfolios and machine learning interpretability for robust cryptocurrency investment strategies

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.