This repository contains coursework, group work projects (GWPs), and applied notebooks completed as part of my graduate-level Financial Engineering program. The work integrates mathematical finance, statistics, machine learning, and software implementation, with an emphasis on translating theory into practical financial models.
Projects are organized by subject area, with each folder corresponding to a core course or module in the program.
deep_learning derivative_pricing financial_data machine_learning portfolio_management stochastic_modeling
Each folder contains Jupyter notebooks corresponding to Group Work Projects (GWP1, GWP2, GWP3) or major assignments.
Folder: deep_learning
This section focuses on deep learning techniques applied to financial problems, particularly time series modeling and prediction.
Notebooks:
- dl_gwp1.ipynb: Foundations of deep learning for financial time series
- dl_gwp2.ipynb: Neural network architectures and training considerations
- dl_gwp3.ipynb: Advanced deep learning applications in finance
Key topics:
- Neural networks
- Optimization and regularization
- Financial time series modeling
- Model evaluation and limitations
Folder: derivative_pricing
This section covers mathematical models and numerical methods used to price derivative securities.
Notebooks:
- dp_gwp1.ipynb: Core derivative pricing concepts
- dp_gwp2.ipynb: Numerical methods and implementation
Key topics:
- Risk-neutral valuation
- Option pricing frameworks
- Monte Carlo simulation
- Numerical approximation techniques
Folder: financial_data
This section focuses on financial data acquisition, preprocessing, and exploratory analysis.
Notebooks:
- fd_gwp1.ipynb: Financial data sourcing and cleaning
- fd_gwp2.ipynb: Exploratory data analysis
- fd_gwp3.ipynb: Feature engineering and diagnostics
Key topics:
- Market and economic data
- Time series analysis
- Data quality and cleaning
- Statistical diagnostics
Folder: machine_learning
This section applies classical machine learning methods to financial modeling tasks.
Notebooks:
- ml_gwp1.ipynb: Supervised learning fundamentals
- ml_gwp2.ipynb: Model selection and evaluation
- ml_gwp3.ipynb: Advanced machine learning applications in finance
Key topics:
- Regression and classification
- Bias-variance tradeoff
- Feature selection
- Cross-validation and performance metrics
Folder: portfolio_management
This section focuses on portfolio construction, optimization, and risk management.
Notebooks:
- pm_gwp1.ipynb: Portfolio theory foundations
- pm_gwp2.ipynb: Portfolio optimization techniques
- pm_gwp3.ipynb: Advanced portfolio construction and analysis
Key topics:
- Mean-variance optimization
- Risk and return tradeoffs
- Asset allocation
- Portfolio performance evaluation
Folder: stochastic_modeling
This section focuses on stochastic processes used in financial modeling.
Notebooks:
- sm_gwp3.ipynb: Stochastic process modeling and simulation
Key topics:
- Stochastic differential equations
- Interest rate and asset models
- Monte Carlo simulation
- Model calibration
Python Jupyter Notebook NumPy, pandas, SciPy scikit-learn matplotlib and seaborn
These notebooks were developed for academic purposes as part of a graduate program. Results depend on model assumptions and are intended for educational use, not financial advice.
Alfonso Meraz Graduate Student in Financial Engineering Background in software engineering, quantitative finance, and machine learning