Learning to Manage Investment Portfolios beyond Simple Utility Functions

2025-10-30

AI Summary

This paper addresses the challenge of characterizing portfolio managers’ multi-objective decision-making, which resists explicit utility function specification. We propose a reward-free, label-free generative modeling framework based on conditional Generative Adversarial Networks (cGANs). The method learns latent strategy representations by modeling the joint distribution of fund holdings and market data, directly estimating the conditional distribution of portfolio weights given stock-level features, historical returns, prior weights, and latent strategy variables. Crucially, it obviates pre-specified utility functions and automatically disentangles implicit investment objectives. Furthermore, it enables linearly interpretable style decomposition—e.g., growth vs. value—via learned latent factors. Empirical evaluation across 1,436 U.S. equity mutual funds demonstrates that the model accurately identifies dominant investment styles while uncovering heterogeneous strategy characteristics—including turnover, concentration, and factor exposures—thereby establishing a novel paradigm for understanding real-world asset management behavior.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

While investment funds publicly disclose their objectives in broad terms, their managers optimize for complex combinations of competing goals that go beyond simple risk-return trade-offs. Traditional approaches attempt to model this through multi-objective utility functions, but face fundamental challenges in specification and parameterization. We propose a generative framework that learns latent representations of fund manager strategies without requiring explicit utility specification. Our approach directly models the conditional probability of a fund's portfolio weights, given stock characteristics, historical returns, previous weights, and a latent variable representing the fund's strategy. Unlike methods based on reinforcement learning or imitation learning, which require specified rewards or labeled expert objectives, our GAN-based architecture learns directly from the joint distribution of observed holdings and market data. We validate our framework on a dataset of 1436 U.S. equity mutual funds. The learned representations successfully capture known investment styles, such as "growth" and "value," while also revealing implicit manager objectives. For instance, we find that while many funds exhibit characteristics of Markowitz-like optimization, they do so with heterogeneous realizations for turnover, concentration, and latent factors. To analyze and interpret the end-to-end model, we develop a series of tests that explain the model, and we show that the benchmark's expert labeling are contained in our model's encoding in a linear interpretable way. Our framework provides a data-driven approach for characterizing investment strategies for applications in market simulation, strategy attribution, and regulatory oversight.

Problem

• Modeling complex fund manager strategies beyond simple utility functions
• Learning latent investment representations without explicit reward specification
• Capturing heterogeneous portfolio objectives using generative adversarial networks

Innovation

• Generative framework learns latent fund manager strategies
• GAN-based architecture models portfolio weights distribution
• Learns directly from holdings and market data