Paper: arXiv 2504.06279

Authors: Jingru Wang, Wen Ding, Xiaotong Zhu

Abstract

In the modern financial sector, the exponential growth of data has made efficient and accurate financial data analysis increasingly crucial. Traditional methods, such as statistical analysis and rule-based systems, often struggle to process and derive meaningful insights from complex financial information effectively. These conventional approaches face inherent limitations in handling unstructured data, capturing intricate market patterns, and adapting to rapidly evolving financial contexts, resulting in reduced accuracy and delayed decision-making processes. To address these challenges, this paper presents an intelligent financial data analysis system that integrates Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) technology. Our system incorporates three key components: a specialized preprocessing module for financial data standardization, an efficient vector-based storage and retrieval system, and a RAG-enhanced query processing module. Using the NASDAQ financial fundamentals dataset from 2010 to 2023, we conducted comprehensive experiments to evaluate system performance. Results demonstrate significant improvements across multiple metrics: the fully optimized configuration (gpt-3.5-turbo-1106+RAG) achieved 78.6% accuracy and 89.2% recall, surpassing the baseline model by 23 percentage points in accuracy while reducing response time by 34.8%. The system also showed enhanced efficiency in handling complex financial queries, though with a moderate increase in memory utilization. Our findings validate the effectiveness of integrating RAG technology with LLMs for financial analysis tasks and provide valuable insights for future developments in intelligent financial data processing systems.

Complexity vs Empirical Score

  • Math Complexity: 1.0/10
  • Empirical Rigor: 7.5/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper presents a practical application of LLM-RAG technology using a real financial dataset (NASDAQ) with quantitative results like accuracy and recall, but lacks advanced mathematical modeling or derivations.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Develop intelligent financial data analysis system"] --> B["Data Input<br>NASDAQ Fundamentals 2010-2023"]
  B --> C["Key Methodology<br>LLM-RAG Integration"]
  C --> D["Computational Processes<br>Preprocessing + Vector Storage + Query Processing"]
  D --> E["System Configurations<br>gpt-3.5-turbo-1106 vs Baseline"]
  E --> F{"Key Findings/Outcomes"}
  F --> G["Accuracy: 78.6%<br>Improvement: +23 pp over baseline"]
  F --> H["Recall: 89.2%<br>Response Time: -34.8% reduction"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes an intelligent financial data analysis system that combines Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) technology.

Source sentence
this paper presents an intelligent financial data analysis system that integrates Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) technology.

Assumes

No explicit assumptions found in the text.

Data

  • NASDAQ Financial Fundamentals dataset · Kaggle fundamentals public
    2010-2023 · major technology companies such as Apple, Microsoft, Google
    Source sentence
    Using the NASDAQ financial fundamentals dataset from 2010 to 2023, we conducted comprehensive experiments to evaluate system performance.

Recognised sources: Kaggle

Costs

Not applicable The paper reports no trading or execution result.

Finds 2

  • The fully optimized configuration (gpt-3.5-turbo-1106+RAG) achieved 78.6% accuracy and 89.2% recall, surpassing the baseline model by 23 percentage points in accuracy while reducing response time by 34.8%. performance
    Source sentence
    the fully optimized configuration (gpt-3.5-turbo-1106+RAG) achieved 78.6% accuracy and 89.2% recall, surpassing the baseline model by 23 percentage points in accuracy while reducing response time by 34.8%.
  • The gpt-3.5-turbo-1106+RAG configuration demonstrated exceptional performance, reaching an accuracy rate of 78.6% and a recall rate of 89.2%. performance
    Source sentence
    gpt-3.5-turbo-1106+RAG configuration demonstrated exceptional performance, reaching an accuracy rate of 78.6% and a recall rate of 89.2%.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 6 related papers). Coverage is partial, so this is neither replication nor refutation.

Cited by 1 paper in the archive (1 by independent authors): VERAFI: Verified Agentic Financial Intelligence through … (discusses its findings)

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.