Skip to content
View lucalullo's full-sized avatar
185 followers · 510 following

Block or report lucalullo

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.

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
lucalullo/README.md

Luca Lullo - Data Scientist

Data Scientist indipendente specializzato in data analysis, data cleaning avanzato e machine learning.

Sviluppo dataset, notebook e modelli predittivi in diversi ambiti, con particolare attenzione all’analisi di dati pubblici, sistemi istituzionali e dinamiche socio-economiche.

Mi occupo di:

  • integrazione di dataset eterogenei;
  • costruzione di indicatori comparabili;
  • sviluppo di analisi riproducibili;
  • auditing e controllo della qualità dei dati;
  • modelli predittivi e supporto alle decisioni.

Utilizzo principalmente Python per trasformare dati complessi in informazioni affidabili, comprensibili e utilizzabili.

🏆 Kaggle Expert in 2 categorie

Kaggle

  • Datasets Expert: rank 79 su 10.426 - miglior rank raggiunto: 76 - 11 medaglie
  • Notebooks Expert: rank 751 su 62.362 - 13 medaglie

🛠️ Stack tecnologico

Python Pandas Scikit-learn XGBoost LightGBM CatBoost TensorFlow Keras PyTorch Plotly SQL Jupyter Git

📂 Progetti in evidenza

Progetto Ambito Strumenti e caratteristiche
Customer Support Agent AI Agent / Human-in-the-loop Google ADK, Gemini, classificazione delle email ed escalation umana
Building AI Agent AI Agent from scratch Python puro, routing, parsing, esecuzione di tool e memoria
Global Inequality and Poverty - 1980-2024 Socio-economia Data integration e costruzione di indicatori globali comparabili
Italian Justice System Workload Dati istituzionali Analisi civile e penale 2003-2024, auditing e controllo dei dati
Home Credit Default Risk Credit Risk / Machine Learning XGBoost, LightGBM, SHAP e feature engineering
Global Emissions & Temperature - 1950–2024 Clima e serie storiche Analisi di CO₂, gas serra e temperature globali

🔎 Aree di interesse

  • Data quality e data cleaning
  • Machine learning applicato
  • Explainable AI
  • AI agent e automazione
  • Dati pubblici e istituzionali
  • Analisi socio-economiche
  • Serie storiche e indicatori comparabili
  • Ricerca riproducibile

📬 Contatti

LinkedIn Kaggle GitHub

Pinned Loading

  1. House-prices House-prices Public

    Predicting house prices using Ridge Regression, Skewness transformation and Advanced Feature Engineering.

    Jupyter Notebook 1 1

  2. Home-credit-default-risk Home-credit-default-risk Public

    Machine learning project to predict credit default risk with feature engineering, XGBoost and SHAP interpretability.

    Jupyter Notebook

  3. lucalullo lucalullo Public

    1

  4. Customer-support-agent Customer-support-agent Public

    About Kaggle Hackathon Capstone Project - Customer Support Agent

    Python 2 1

  5. Global-emissions-and-temperature-1950-2024 Global-emissions-and-temperature-1950-2024 Public

    Global climate analysis covering 75 years of CO₂, greenhouse gas emissions and mean surface temperatures across countries (1950–2024). Built with Pandas, Matplotlib, Seaborn and Plotly.

    Jupyter Notebook

  6. building-ai-agent building-ai-agent Public

    Versioned educational project for building an AI agent, with Jupyter notebooks, IT/EN reports and architecture diagrams.

    Jupyter Notebook 1 1