Unifying Asset Ranking and Portfolio Weighting through a Multi-Task Neural Network

Mathis Linger, Ilias Mellouki and Guillaume Boulanger
Additional contact information
Mathis Linger: LEO - Laboratoire d'Économie d'Orleans [2022-...] - UO - Université d'Orléans - UT - Université de Tours - UCA - Université Clermont Auvergne, Drakai Capital
Ilias Mellouki: Drakai Capital
Guillaume Boulanger: Drakai Capital

Post-Print from HAL

Abstract: This study presents a novel approach that integrates asset ranking and portfolio weighting within a single framework. Unlike traditional methods, which separate asset ranking from portfolio weighting, this research employs a multi-task neural network to concurrently learn asset rankings and optimize the number of assets for long and short positions. This innovation aims to better align the investment strategy with investor preferences right from the model prediction phase. To assess its effectiveness, the authors conduct experiments using historical weekly market data from China A-shares. The findings indicate that incorporating portfolio weighting into a multi-task learning framework significantly improves out-of-sample financial performance in contrast to benchmark methods that rely on heuristics or historical estimations.

Date: 2025-04-30
References: Add references at CitEc
Citations:

Published in The Journal of Financial Data Science, 2025, 7 (2), pp.84-104. ⟨10.3905/jfds.2025.1.190⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-05125910

DOI: 10.3905/jfds.2025.1.190

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().