Financial News Sentiment and Stock Market Correlation Analysis

This project focuses on the detailed analysis of financial news sentiment and its correlation with stock market movements. By leveraging natural language processing (NLP) techniques, sentiment analysis, and advanced financial analytics, this analysis aims to uncover meaningful insights that can enhance financial forecasting accuracy. The ultimate goal is to develop innovative strategies that utilize news sentiment as a predictive tool for stock market trends.

Financial News Sentiment and Stock Market Correlation Analysis - Task 1

This branch focuses on Task 1: Exploratory Data Analysis (EDA), where we perform initial analysis on the financial news dataset to uncover insights and set the foundation for further analysis.

Table of Contents

1. Project Overview

2. Business Objective

3. Dataset Overview

4. Tasks and Deliverables

5. Installation

6. Usage

7. Contributing

8. License

9. Task 1 Overview

Project Overview

This project focuses on analyzing a large corpus of financial news data to discover correlations between news sentiment and stock market movements. It encompasses data engineering, financial analytics, and machine learning engineering to enhance predictive analytics capabilities at Nova Financial Solutions.

Business Objective

Nova Financial Solutions aims to enhance its predictive analytics capabilities to significantly boost its financial forecasting accuracy and operational efficiency through advanced data analysis. This involves:

• Performing sentiment analysis on financial news headlines.
• Establishing statistical correlations between sentiment scores and stock price movements.
• Providing actionable insights and investment strategies based on the analysis.

Dataset Overview

The Financial News and Stock Price Integration Dataset (FNSPID) contains:

• headline: Title of the news article.
• url: Direct link to the full news article.
• publisher: Author/creator of the article.
• date: Publication date and time.
• stock: Stock ticker symbol.

Tasks and Deliverables

Week 1:

• Task 1: Exploratory Data Analysis (EDA)

  • Descriptive Statistics
  • Text Analysis (Sentiment Analysis & Topic Modeling)
  • Time Series Analysis
  • Publisher Analysis

• Task 2: Quantitative Analysis using PyNance and TA-Lib

  • Load and prepare stock price data
  • Apply technical analysis indicators
  • Visualize the data

• Task 3: Correlation Between News and Stock Movement

  • Align datasets by dates
  • Perform sentiment analysis on news headlines
  • Calculate daily stock returns and correlation with sentiment scores

Deliverables:

• Interim Report: Summary of initial findings and partial progress (max 3 pages).
• Final Report: Detailed analysis and insights (up to 10 pages).

Installation

1. Clone the Repository:

   git clone https://github.com/dagiteferi/Financial-News-Sentiment-Stock-Market-Correlation-Analysis.git
   cd Financial-News-Sentiment-Stock-Market-Correlation-Analysis
   

2. Install Dependencies:

pip install -r requirements.txt

** Contributing** Contributions are welcome! Please fork the repository and use a feature branch. Pull requests are warmly welcomed.

How to Contribute

1. Fork the repository: Click the "Fork" button at the top right of this page to create your own copy of the repository.
2. Clone your fork: Clone the forked repository to your local machine.

   git clone https://github.com/your-username/your-repository.git

3. Create a new branch: Create a new branch for your feature or bugfix.

   git checkout -b feature/AmazingFeature

4. Make your changes: Implement your feature or fix the bug. Ensure your code adheres to the project's coding standards and style.
5. Commit your changes: Commit your changes with a descriptive message.

   git add .
   git commit -m 'Add some AmazingFeature'

6. Push your branch: Push your branch to your forked repository.

   git push origin feature/AmazingFeature

7. Create a Pull Request: Go to the repository on GitHub, switch to your branch, and click the New Pull Request button. Provide a detailed description of your changes and submit the pull request.

License Distributed under the MIT License. See LICENSE for more information.

=======

Task 1 Overview

Task 1: Exploratory Data Analysis (EDA)

• Descriptive Statistics: Calculate basic statistics such as headline length, article counts per publisher, and publication dates.
• Text Analysis: Perform sentiment analysis on headlines and identify common keywords or phrases.
• Time Series Analysis: Analyze the frequency of article publication over time and identify trends.
• Publisher Analysis: Identify top publishers and analyze their reporting patterns.

Deliverables for Task 1:

• EDA Report: Summary of initial findings and insights from the exploratory data analysis.