Skip to content
View giannandreadestefano's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report giannandreadestefano

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Giannandrea De Stefano

MSc Economics & Finance candidate at LUISS Guido Carli, focused on quantitative finance, market risk, asset pricing and portfolio analytics. I build empirical finance projects in Python and MATLAB, with applications to prediction markets, derivatives-implied probabilities and multi-asset risk management.


Selected Research Projects

MSc thesis comparing Bitcoin prediction-market probabilities on Polymarket and Kalshi with a DVOL-based Deribit benchmark.

The empirical pipeline covers API-based data collection, contract parsing and classification, timestamp and maturity matching, benchmark construction, bootstrap inference, OLS regressions with robust and clustered standard errors, and monthly and horizon-based robustness checks.

Tools & methods: Python, REST APIs, pandas, market data processing, Black-Scholes-style probability benchmark, bootstrap inference, OLS regressions, clustered standard errors.


Python-based market risk engine covering equities, Treasuries, credit, gold and crypto.

The project includes portfolio construction, volatility forecasting, VaR and Expected Shortfall estimation, stress testing, risk model backtesting and regime-aware risk monitoring. The objective is to evaluate how standard market risk models behave across normal and stressed market conditions.

Tools & methods: Python, pandas, NumPy, SciPy, statsmodels, GARCH, VaR/Expected Shortfall, stress testing, risk attribution, risk model backtesting.


Research project testing whether a systematic long-short cryptocurrency strategy can enhance a traditional 60/40 equity-bond portfolio.

The strategy is based on Size and Risk-Adjusted Momentum signals and was tested on 79 liquid cryptocurrencies, excluding stablecoins, using a framework including CAPM/Fama-French regressions, GARCH models, bootstrap simulations and stress scenarios.

Tools & methods: MATLAB, Python, portfolio backtesting, factor models, GARCH, bootstrap simulation, stress testing.


Selected Case Study

AI Lakehouse for NASA — LUISS Prompt-a-thon 2025

Top 3 project at the LUISS Prompt-a-thon 2025. Co-developed a WatsonX-based AI infrastructure proposal for NASA data governance, mission autonomy and operational efficiency.

Focus: AI strategy, data governance, IBM WatsonX, enterprise architecture.


Technical Stack

Programming & Data Python, MATLAB, R, VBA, Advanced Excel, LaTeX

Finance & Econometrics OLS regressions, CAPM/Fama-French models, GARCH, VaR/Expected Shortfall, Fama-MacBeth tests, bootstrap simulation, stress testing, risk model backtesting, portfolio backtesting

Platforms Bloomberg Terminal, Aladdin, Quantalys, Refinitiv, yfinance, REST APIs


Current Focus

  • Building applied quantitative finance projects in Python and MATLAB
  • Researching cross-market pricing and derivatives-implied probabilities
  • Developing portfolio analytics and market risk tools
  • Preparing for roles in market risk, quantitative finance, portfolio analytics and asset management

Contact

Pinned Loading

  1. GiannandreaDeStefano GiannandreaDeStefano Public

  2. crypto-mispricing-portfolio crypto-mispricing-portfolio Public

    Backtesting a long-short crypto strategy based on Size and Risk-Adjusted Momentum signals.

    MATLAB 1

  3. btc-prediction-market-efficiency btc-prediction-market-efficiency Public

    MSc thesis on BTC prediction-market efficiency using Polymarket, Kalshi and Deribit data

    Jupyter Notebook

  4. quant-risk-lab quant-risk-lab Public

    A Python-based multi-asset market risk engine for VaR, Expected Shortfall, volatility forecasting, stress testing, and regime-aware risk analysis.

    Jupyter Notebook