Module 1: Market Intelligence with NLP and Network Analysis
Part of Specialization: Data Visualization Using Python
Self-paced - Mentor-led - 7 weeks - 3 Modules
Module 1: Market Intelligence with NLP and Network Analysis
🕑 8 Lessons · ~24 hours · Deliverable: Interactive network visualization of financial news
Language is data. Every earnings announcement, every analyst report, every market news headline is a dataset waiting to be mapped. In Module 1, you become an investment research analyst — setting up a professional workspace, scraping financial news, mining text for meaning, pulling live price data, and rendering the relationships between companies, topics, and events as an interactive network graph.
You pick a market sector that interests you in Lesson 1 and use it throughout the module. The demo walkthroughs use the AI and tech sector. Your exercises use your own. By the end, you have an original piece of analysis — not a reproduction of someone else’s tutorial.
This is also where you meet Gemini as a coding copilot — embedded from Lesson 3 onward and present in every lesson that follows.
The Investment Research Analyst and Python Tools
What an investment research analyst does — and how Python replaces the expensive terminal. The module project, the tools you’ll use, and your first decision: choosing the sector you’ll analyse.
Setting Up the Python Workspace
Folder structure, Google Drive organisation, and project conventions that keep your work reproducible and shareable. Mounting Drive and setting path variables — the standard opening for every notebook in this course.
Setting Up Your Colab Workspace and AI Copilot
Installing and managing packages in Colab. Pinning versions with requirements.txt. Introducing the Gemini sidebar — how to prompt it, what it gets right, and where to verify before you apply.
Accessing Web Data with Data Scraping
APIs, RSS feeds, and scraping — when to use each. Using feedparser and BeautifulSoup to pull financial news. The legal and ethical boundaries every analyst must understand before scraping anything.
Text Mining Financial News
Tokenising, cleaning, and counting a financial news corpus at scale. Frequency analysis, stopword removal, and term extraction — turning unstructured headlines into structured data.
Intro to NLP and Network Analysis
Named entity recognition to extract companies, people, and topics. Sentiment analysis. Co-occurrence as the basis for network graphs. Nodes, edges, and weights — the conceptual foundation before you build.
Creating Network Visualizations
Building and rendering graphs with NetworkX and Pyvis. Layout algorithms, node sizing by frequency, edge weights by co-occurrence, community colouring — making the invisible structure of financial news visible.
Portfolio and Branding
Packaging the Module 1 project for employers and clients. Publishing to GitHub. Writing about your analysis for a financial or business audience — not a technical one.
📄 Module 1 Deliverable: A GitHub-published network visualization showing how companies, topics, and events relate in your chosen sector — built from a scraped and cleaned financial news corpus, with an annotated Colab notebook and a LinkedIn post describing what you found and why it matters.
Contact
Talk to us
Have questions? We’re here to help! Whether you’re curious to learn more, want guidance on applying, or need insights to make the right decision—reach out today and take the first step toward transforming your career.