Trade Selection with Supervised Learning and Optimal Coordinate Ascent (OCA) - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Trade Selection with Supervised Learning and Optimal Coordinate Ascent (OCA)

Résumé

Can we dynamically extract some information and strong relationship between some financial features in order to select some financial trades over time? Despite the advent of representation learning and end-to-end approaches, mainly through deep learning, feature selection remains a key point in many machine learning scenarios. This paper introduces a new theoretically motivated method for feature selection. The approach that fits within the family of embedded methods, casts the feature selection conundrum as a coordinate ascent optimization with variables dependencies materialized by block variables. Thanks to a limited number of iterations, it proves efficiency for gradient boosting methods, implemented with XGBoost. In case of convex and smooth functions, we are able to prove that the convergence rate is polynomial in terms of the dimension of the full features set. We provide comparisons with state of the art methods, Recursive Feature Elimination and Binary Coordinate Ascent and show that this method is competitive when selecting some financial trades.
Fichier non déposé

Dates et versions

hal-03767962 , version 1 (02-09-2022)

Identifiants

Citer

David Saltiel, Eric Benhamou, Rida Laraki, Jamal Atif. Trade Selection with Supervised Learning and Optimal Coordinate Ascent (OCA). 5th ECML PKDD Workshop, MIDAS 2020, Sep 2020, Ghent, Belgium. pp.1-15, ⟨10.1007/978-3-030-66981-2_1⟩. ⟨hal-03767962⟩
47 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More