From Deep Learning to LLMs: A survey of AI in Quantitative Investment

ArXiv ID: 2503.21422 “View on arXiv”

Authors: Unknown

Abstract

Quantitative investment (quant) is an emerging, technology-driven approach in asset management, increasingy shaped by advancements in artificial intelligence. Recent advances in deep learning and large language models (LLMs) for quant finance have improved predictive modeling and enabled agent-based automation, suggesting a potential paradigm shift in this field. In this survey, taking alpha strategy as a representative example, we explore how AI contributes to the quantitative investment pipeline. We first examine the early stage of quant research, centered on human-crafted features and traditional statistical models with an established alpha pipeline. We then discuss the rise of deep learning, which enabled scalable modeling across the entire pipeline from data processing to order execution. Building on this, we highlight the emerging role of LLMs in extending AI beyond prediction, empowering autonomous agents to process unstructured data, generate alphas, and support self-iterative workflows.

Keywords: quantitative investment, deep learning, large language models (LLMs), alpha strategy, autonomous agents, Multi-Asset

Complexity vs Empirical Score

  • Math Complexity: 3.0/10
  • Empirical Rigor: 1.5/10
  • Quadrant: Philosophers
  • Why: The paper is a survey that reviews AI applications in quant finance, focusing on high-level concepts and evolutionary trends rather than novel mathematical derivations or empirical backtests. It lacks the dense formulas, code, or implementation details characteristic of high-math or high-rigor research.
  flowchart TD
    A["Research Goal: AI in Quant Investment"] --> B["Data Sources<br>Traditional + Unstructured Data"]
    B --> C["Methodology Stages<br>1. Traditional Statistical (Human Features)<br>2. Deep Learning (Scalable Models)<br>3. LLMs & Agents (Autonomous Workflow)"]
    C --> D["Computational Processes<br>Alpha Strategy Pipeline<br>Feature Generation → Signal Prediction → Execution"]
    D --> E["Key Findings/Outcomes<br>- AI improves predictive modeling<br>- LLMs extend beyond prediction<br>- Autonomous agents enable self-iterative workflows<br>- Potential paradigm shift in asset management"]