Multimodal Gen-AI for Fundamental Investment Research

Paper: arXiv 2401.06164

Authors: Lezhi Li, Ting-Yu Chang, Hai Wang

Abstract

This report outlines a transformative initiative in the financial investment industry, where the conventional decision-making process, laden with labor-intensive tasks such as sifting through voluminous documents, is being reimagined. Leveraging language models, our experiments aim to automate information summarization and investment idea generation. We seek to evaluate the effectiveness of fine-tuning methods on a base model (Llama2) to achieve specific application-level goals, including providing insights into the impact of events on companies and sectors, understanding market condition relationships, generating investor-aligned investment ideas, and formatting results with stock recommendations and detailed explanations. Through state-of-the-art generative modeling techniques, the ultimate objective is to develop an AI agent prototype, liberating human investors from repetitive tasks and allowing a focus on high-level strategic thinking. The project encompasses a diverse corpus dataset, including research reports, investment memos, market news, and extensive time-series market data. We conducted three experiments applying unsupervised and supervised LoRA fine-tuning on the llama2_7b_hf_chat as the base model, as well as instruction fine-tuning on the GPT3.5 model. Statistical and human evaluations both show that the fine-tuned versions perform better in solving text modeling, summarization, reasoning, and finance domain questions, demonstrating a pivotal step towards enhancing decision-making processes in the financial domain. Code implementation for the project can be found on GitHub: https://github.com/Firenze11/finance_lm.

Complexity vs Empirical Score

• Math Complexity: 2.0/10
• Empirical Rigor: 5.5/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper focuses on applied LLM fine-tuning (LoRA, instruction tuning) for financial research automation with minimal mathematical derivation. It offers practical empirical evaluations (both statistical and human) and strong reproducibility thanks to an open GitHub repository, though the underlying modeling techniques rely heavily on standard modern NLP frameworks.

Research Flowchart

  flowchart TD
    A["Research Goal: Automate fundamental investment research & idea generation"] --> B["Data Inputs: Research reports, memos, news, & time-series data"]
    B --> C["Model Fine-Tuning: Base Llama-2-7b-chat & GPT-3.5"]
    C --> D["Training Methods: Unsupervised LoRA, Supervised LoRA, & Instruction Fine-Tuning"]
    D --> E["Evaluation: Statistical metrics & human domain evaluation"]
    E --> F["Outcomes: Enhanced financial reasoning, summarization, & automated AI agent prototype"]

Cited References (11)

1. Lora: Low-rank adaptation of large language models (2021) — link
2. Large Language Models Are Zero-Shot Time Series Forecasters (2023) — link
3. Temporal Data Meets LLM – Explainable Financial Time Series Forecasting (2023) — link
4. LLM4TS: Two-Stage Fine-Tuning for Time-Series Forecasting with Pre-Trained LLMs (2023) — link
5. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2021) — link
6. JPM_DeepFin_with_Microso_2023-09-21_4517766 (2023)
7. BloombergGPT: A Large Language Model for Finance (2023)
8. Scrolls: Standardized comparison over long language sequences (2022) — link

0 of 11 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.