AI-Powered Stock Research Generator with Automated Financial Charting

This tool automates the production of financial research reports from inception to final draft. By providing a stock ticker, the system initiates an automated process that gathers financial statements, ownership structures, and relevant industry news. An AI engine then scrutinizes the raw data to compare peers, identify emerging trends, and highlight potential risks. The final output is a structured report featuring integrated charts, data visualizations, and a definitive investment recommendation. Reports are available in both Markdown and Word formats. Furthermore, a built-in workflow engine automates broader industry and macroeconomic research. The data analysis agent is capable of processing Chinese-language queries, generating its own analysis scripts, and producing graphs with proper Chinese labeling. It is designed specifically to make equity research both faster and more precise.

Core Features

Multi-Source Data Aggregation: Automatically retrieves financial reports, shareholder structures, industry benchmarks, and company fundamentals.

Intelligent Financial Analysis: The AI performs comprehensive quantitative assessments, including growth rates, profitability margins, debt-to-equity ratios, peer benchmarking, and forward-looking estimates.

Automated Visualization: Dynamically generates professional-grade financial charts and data visualizations.

In-Depth Report Composition: Delivers a full-length equity research report complete with a specific investment thesis.

Modular Workflow Engine: Executes automated sequences for specialized industry studies and macroeconomic environmental scans.

System Architecture

The platform utilizes a five-layer architecture to transform raw data into professional reports.

Data Input Layer

• Receives a stock code and activates the data collection modules.
• Retrieves financial data, shareholder information, industry context, and corporate history.

Core Processing Layer

• The data analysis agent manages three primary functions: AI-driven financial auditing, intelligent visualization, and trend forecasting.

Workflow Engine

• Orchestrates specialized research flows for industry sectors and macroeconomic factors.
• Decision nodes trigger targeted searches and content generation based on findings.

Report Generation Layer

• Basic Builder: Merges financial analysis, visuals, and projections.
• Integrated Builder: Synthesizes search results with generated narrative content.
• Deep Research Builder: Consolidates all outputs into a finalized, high-fidelity document.

Output Formats

• Results are delivered as Markdown reports, Word documents, standalone charts, and investment rating summaries.

Key Capabilities

1. Multi-Source Data Integration

• Financials: Fetches balance sheets, income statements, and cash flow data via the akshare interface.
• Ownership: Scrapes current shareholder data from financial platforms such as 10jqka.
• Industry Intelligence: Uses DuckDuckGo search to aggregate sector-specific news and market sentiment.
• Corporate Profile: Compiles basic company facts and primary business descriptions.

2. Intelligent Analysis Engine

• Financial Health Audit: Reviews revenue growth, operating margins, solvency, and efficiency ratios.
• Peer Comparison: Automatically identifies competitors and conducts side-by-side metric evaluations.
• Forecasting: Constructs projections and valuation models based on historical performance.
• Risk Assessment: Evaluates financial, industry-specific, and broader market risks.

3. Professional Report Output

• Structured Layout: Adheres to standard institutional equity research formats.
• Visuals: Creates professional charts with full support for Chinese character rendering.
• Investment Opinion: Provides a clear rating and actionable recommendation.
• Export Versatility: Compatible with Markdown, Word, and other formats.

Installation and Setup

Requirements

• Python 3.8 or newer
• OpenAI API key (or a compatible LLM provider)

Steps

1. Clone the repository:

   git clone https://github.com/li-xiu-qi/financial_research_report
   cd financial_research_report
   

2. Install the necessary dependencies:

   pip install -r requirements.txt
   

3. Configure the environment: Create a .env file in the root directory:

   OPENAI_API_KEY=your_openai_api_key
   OPENAI_BASE_URL=https://api.openai.com/v1
   OPENAI_MODEL=gpt-4
   

Usage Examples

Basic Report Generation

from research_report_generator import generate_report

target_company = "SenseTime"
target_company_code = "00020"
target_company_market = "HK"

generate_report(target_company, target_company_code, target_company_market)

Integrated Report Generation

from integrated_research_report_generator import IntegratedResearchReportGenerator

generator = IntegratedResearchReportGenerator()
generator.run_full_pipeline()

Industry Research Workflow

from industry_workflow import IndustryResearchFlow
from pocketflow import Flow

flow = Flow()
flow.add_node("industry_research", IndustryResearchFlow())

shared_data = {
    "industry": "Artificial Intelligence",
    "context": []
}

flow.run(shared_data)

Data Sources

• Financial Statements: East Money financial interface.
• Ownership Data: 10jqka shareholder documentation.
• Company Profiles: 10jqka business summaries.
• Industry News: DuckDuckGo search aggregation.
• Market Data: akshare financial data ecosystem.

Module Details

Data Analysis Agent

• Interprets natural language queries in Chinese.
• Generates Python scripts for custom data analysis.
• Renders financial charts with accurate Chinese text support.
• Produces analysis reports in Markdown or Word.

Workflow Engine (PocketFlow)

• Uses decision nodes to determine the subsequent analytical path.
• Automatically searches for and integrates missing information.
• Populates templated report sections dynamically.

Data Collection Tools

• Supports financial data for both A-shares and Hong Kong stocks.
• Parses complex ownership structures.
• Uses AI to identify relevant peer groups.
• Aggregates and cleans data from multiple disparate sources.

Supported Analysis Types

Quantitative Financial Analysis

• Revenue growth trajectories.
• Net profit fluctuations.
• Cash flow health and stability.
• Balance sheet structural integrity.

Valuation Models

• Relative valuation using P/E, P/B, and industry benchmarks.
• Discounted Cash Flow (DCF) models.
• Fair value range estimation.

Risk Management

• Quantitative financial risk indicators.
• Industry-specific cyclical risks.
• Market liquidity assessments.
• Corporate governance and management concerns.

Sample Report Structure

Generated reports typically include the following sections:

• Company Overview: Corporate history, primary business segments, and ownership.
• Financial Analysis: Comprehensive statement review, key ratio analysis, and trends.
• Industry Analysis: Market share, competitive landscape, and sector-wide developments.
• Valuation: Model outputs, fair value estimations, and the final investment rating.
• Risk Disclosure: Primary vulnerabilities and potential mitigation factors.

Customization

LLM Configuration The system is compatible with:

• OpenAI GPT models.
• Any OpenAI-compatible API endpoint.
• Locally hosted large language models.

Analysis Parameters

• Customizable historical lookback periods.
• Adjustable peer group selection criteria.
• Configurable risk assessment thresholds.
• Variable levels of report detail.