ResearchTrend.AI
  • Papers
  • Communities
  • Organizations
  • Events
  • Blog
  • Pricing
  • Feedback
  • Contact Sales
Papers
Communities
Social Events
Terms and Conditions
Pricing
Contact Sales
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2507.09916
63
1
v1v2v3 (latest)

Solving dynamic portfolio selection problems via score-based diffusion models

14 July 2025
Ahmad Aghapour
Erhan Bayraktar
Fengyi Yuan
    DiffM
ArXiv (abs)PDFHTML
Main:34 Pages
5 Figures
Bibliography:5 Pages
4 Tables
Abstract

In this paper, we tackle the dynamic mean-variance portfolio selection problem in a {\it model-free} manner, based on (generative) diffusion models. We propose using data sampled from the real model P\mathcal PP (which is unknown) with limited size to train a generative model Q\mathcal QQ (from which we can easily and adequately sample). With adaptive training and sampling methods that are tailor-made for time series data, we obtain quantification bounds between P\mathcal PP and Q\mathcal QQ in terms of the adapted Wasserstein metric AW2\mathcal A W_2AW2​. Importantly, the proposed adapted sampling method also facilitates {\it conditional sampling}. In the second part of this paper, we provide the stability of the mean-variance portfolio optimization problems in AW2\mathcal A W _2AW2​. Then, combined with the error bounds and the stability result, we propose a policy gradient algorithm based on the generative environment, in which our innovative adapted sampling method provides approximate scenario generators. We illustrate the performance of our algorithm on both simulated and real data. For real data, the algorithm based on the generative environment produces portfolios that beat several important baselines, including the Markowitz portfolio, the equal weight (naive) portfolio, and S\&P 500.

View on arXiv
Comments on this paper