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

2025-03-27

AI Summary

This paper addresses the lack of systematic frameworks and paradigmatic advances in applying AI to quantitative investing. It proposes an AI-driven three-stage evolutionary model—statistical modeling → end-to-end deep learning modeling → LLM-empowered autonomous agents—and introduces the first comprehensive AI-powered quantitative investment framework spanning research, signal generation, execution, and risk control. Its core contribution is an LLM-driven self-iterative Alpha generation paradigm, integrating fine-tuning, retrieval-augmented generation (RAG), and agent architecture to automate strategy discovery, backtesting, and optimization in a closed loop. This paradigm transcends traditional predictive limitations by significantly enhancing the understanding and utilization of unstructured financial data. Empirically, the framework integrates CNNs, RNNs, Transformers, financial time-series modeling techniques, and multi-source heterogeneous data processing. It delivers a production-ready LLM–quantitative synergy architecture and an evaluation benchmark for institutional practitioners.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

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.

Problem

• Exploring AI's role in quantitative investment pipelines
• Assessing deep learning impact on predictive financial modeling
• Evaluating LLMs for autonomous agent-based quant strategies

Innovation

• Deep learning enables scalable quant pipeline modeling
• LLMs extend AI beyond prediction in finance
• Autonomous agents process data and generate alphas