Aspiring Data Scientist & Kaggle Master.

  • Age: 26
  • Education: Double Masters Degrees
  • Language: Italian, English, Japanese
  • Birthday: 19 February 1995
  • City: Parma, Italy
  • Hobbies: Data Science, Videogames, Guitar

Aspiring Data Scientist, Kaggle Master and Double Degree (MSc) graduate student in Automation and Control Engineering at Keio University (Tokyo) and Politecnico di Milano (Milan). My 2 years experience in Tokyo as an International student made me able to adapt quickly to sudden changes and adopt the positive aspects of different cultures. I actively work on Data Science and Machine Learning projects using Deep Learning and state-of-the-art algorithms to extract insights and answer valuable questions by analyzing data.

Data Science Skills

Python 100%
SQL 80%
PySpark 80%
Tensorflow 90%
PyTorch 90%
XGBoost 100%

Resume

Education in Italy

Masters Degree in Automation and Control Engineering

2020 - 2021

Politecnico di Milano, Milan, Italy

  • Master of Science in Control and Automation
  • Adaptive Control approaches to Non-linear System Control
  • Model Identification and Data Analysis techniques
  • Model Predictive Control in the Industrial Field

Bachelors Degree in Automation and Control Engineering

2015 - 2018

Politecnico di Milano, Milan, Italy

  • Fundamentals of Automation, Electronics and Mechanical engineering.
  • Robotics and linear control techniques

Education in Japan

Masters Degree in Engineering

2018 - 2020

Keio University, Tokyo, Japan

  • Master of Science in Engineering
  • Adaptive Control approaches to Non-linear System Control
  • Computer Vision and Neural Networks applications

Data Science Projects

Forecasting COVID19 new cases in Italy with Machine Learning.

The project is about modeling daily COVID19 cases in Italy by Machine Learning algorithms, with the final goal of forecasting the cases for future days. In particular, the time series modeling has been performed by Prophet (by Facebook), Neural Prophet and SARIMAX models. All the three models achieved similar results in terms of RMSE and MAPE, and highlighted insightful trends and seasonality in the data.

Employee Data Analysis by PySpark, SQL and Salary Prediction by Gradient Boosted Trees.

Dataset Analysis of 1'000'000 employers data by PySpark and SQL to find useful insights on the data. In addition, Feature Engineering and Data Preprocessing was conducted on the dataset, and eventually Machine Learning modeling by Gradient Boosted Tree was performed to predict the employees’ salary.

Twitter Sentiment Analayis using BERT and RoBERTa Transformer models

This project is about the analysis of tweets about coronavirus, with the goal of performing a Sentiment Analysis using BERT and roBERTa algorithms to predict the emotion of a tweet (Positive, Negative or Neutral). In particular, both BERT and ROBERTA will be fine tuned using the given dataset in order to improve the model overall performance.

Heart Failure Prediction by PyTorch and Optuna

The Projects focuses on the analysis of 918 patients using 11 clinical features for predicting heart disease events. In particular, the prediction has been performed using Neural Networks by PyTorch and PyTorch Lightning frameworks, carrying the hyperparameters optimization with OPTUNA library (Tree-structured Parzen Estimator).

Engineering job placement analysis, hypothesis testing and placement prediction by CATBoost and XGBoost

The project focused on analyzing the main factors that determines if an engineering student can get placed or not based on some features. In particular, hypothesis testing has been carried out to confirm relationships between features identified by data visualization. Finally, CATBoost and XGBoost algorithms have been trained to perform the placement prediction.

Laptop Dataset Analysis and Price Prediction with XGBoost

The project is about the analysis of a dataset containing data about laptops to understand what determines price in a laptop. Before exploring the dataset, deep feature Engineering has been performed to extract useful features. Later, XGBoost and Random Forest algorithms have been trained to perform the prediction of the laptop price given the engineered features.

Contact

You contact me at my email c.ludo1995@gmail.com or on social medias :)