Economist × Data Scientist | Bridging Theory and Practice
I develop robust statistical methods and AI frameworks for decision-making under uncertainty, with applications in economics, finance, and complex systems. Currently applying for PhD programs in Decision Analytics and Systems Science.
Core Interest: Agent-Based Decision Analytics in Economic Networks
Methodology: Robust machine learning for high-dimensional economic data
Applications: Supply chain resilience, financial risk modeling, infrastructure prediction
Philosophy (2 years) → Governance & International Relations → Economics & Finance → AI & Machine Learning
Currently completing CESMA Master in AI/ML/Statistics at Tor Vergata University of Rome.
gas-networks-risk-forecasting - Ensemble models for infrastructure resilience prediction using geospatial data, CTGAN synthetic generation, and SHAP explainability.
Alpine Climate Challenge - Multi-source environmental prediction combining Copernicus, NOAA, and regional datasets.
robust-portfolio-optimization - Novel PFSE/SSRE estimators achieving 15-20% performance improvements over traditional methods.
Gen-AI-models - Parameter-Efficient Fine-Tuning, AI photo editing, custom RAG chatbot.
Econometrics - MATLAB implementations for salary analysis and time series modeling (GDP, S&P 500 volatility).
Big-Data-Analysis - R-based projects including news popularity prediction, voting patterns clustering, and comprehensive ML pipelines.
Languages & Frameworks: Python, PyTorch, scikit-learn, TensorFlow
Advanced ML: XGBoost, LightGBM, Random Forest, Gradient Boosting
Specialized Techniques: LoRA/QLoRA, Parameter-Efficient Fine-Tuning
Generative Models: CTGAN, TimeGAN for synthetic data generation
Explainability: SHAP, feature importance, model interpretation
Deep Learning: Neural Networks, LSTM, Attention mechanisms
Languages: R, MATLAB, SAS
Time Series: ARIMA, GARCH, ARCH, EWMA, state-space models
Robust Statistics: Contamination-resistant estimators, outlier detection
Financial Modeling: Markowitz optimization, Black-Litterman, risk metrics
Econometric Methods: Panel data, difference-in-differences, IV estimation
Bayesian Analysis: MCMC, posterior inference, hierarchical models
Dimensionality Reduction: PCA, robust PCA, factor analysis
Languages: Python (pandas, NumPy, SciPy), R (tidyverse, data.table), SQL, SAS
Database: MySQL, SQLite, data warehousing concepts
Big Data: Handling large datasets, memory optimization, parallel processing
Web Scraping: BeautifulSoup, Selenium, API integration
Version Control: Git, GitHub, collaborative development
Computing: High-performance computing, cloud platforms
Visualization: ggplot2, matplotlib, seaborn, plotly, Tableau
Interactive Dashboards: Shiny (R), Streamlit, web applications
Reporting: R Markdown, Jupyter, LaTeX, professional documentation
Presentation: Data storytelling, statistical communication
Financial Engineering: Portfolio optimization, risk management, derivatives
Network Analysis: Graph theory, network metrics, community detection
Geospatial Analysis: Geographic data processing, spatial statistics
Infrastructure Analytics: Risk forecasting, resilience modeling
academic-writing - Collection of theoretical research and analysis:
- Russell's Paradox in Economics - Foundational challenges in mathematical economics
- Master's Thesis - High-dimensional portfolio optimization under sparse contamination
- BADGER Index Analysis - Novel GDP measurement approach submitted to Rethinking Economics
Immediate: PhD Applications in Decision Sciences/Systems Science
Research Vision: Understanding how economic decisions create and influence network structures
Methodology: Combining agent-based modeling with robust statistical inference
Leadership: Secretary General @ Starting Finance Club (70+ members)
Recognition: Selected from 17K+ candidates for Bertelsmann Tech Booster
Upcoming: Oxford Summer School Economic Networks (2025)
Interested in collaborations on: Economic Networks • Robust ML • Decision Science • Complex Systems
📧 stefano.blando@gmail.com | LinkedIn
"Building bridges between economic theory and machine learning to understand decision-making in complex systems."