How syx113/hwz-cas-ml-finance works
Project type and purpose
• This is an educational Machine-Learning-for-Finance repository (HWZ-CAS-ML-Finance).
• It’s a collection of Jupyter notebooks (Exercises & Labs) organized into four “Blocks,” each block covering a different topic (financial fundamentals, predictive modeling, deep learning, time series).
• It uses real-world datasets (credit risk, S&P 500, transactions) to bridge theory and practice.
File structure
• Top-level folders:
• Block1 through Block4 – each with subfolders “Exercises” (.ipynb) and sometimes “Labs” (.ipynb + CSVs).
• Data – raw CSV datasets organized by domain.
• inspect_transactions.ipynb – a standalone exploratory notebook.
• requirements.txt – Python dependencies.
• No web frontend or backend server – it’s a batch/interactive analytics repo.
• Key config: requirements.txt (defines Python 3.11 env + ML libraries).
README for additional insights
• Blocks correspond to course modules: from fundamentals (Block 1) → predictive models (Block 2) → deep learning (Block 3) → time series (Block 4).
• Data sources and use cases are specified.