Emanuele Ferrari

About Me

I am a data Scientist with hands-on experience at Mercedes-Benz, seeking a new, stimulating role.

During my internship, I developed data-driven solutions for the production line, including a high-performing anomaly detection system and an efficient time series ingestion and analysis pipeline. I bring expertise in cloud computing, data engineering, data analysis, and machine learning, and I’m excited to apply these skills to support the company’s digitalization and innovation efforts.

As a Quereinsteiger, my previous career has equipped me with strong problem-solving abilities, experience with international teams and clients, leadership, and a solid understanding of business challenges.

Recent Projects

SECBERT, BERT Model for SEC Documents Analysis

TThis paper will explore the feasibility of deploying a BERT model for U.S. Securities and Exchange Commission (SEC) documents analysis. It is able to label specific sections of SEC filings, as Environmental, Social, and Governance.

Italy Net Trade Visualization

This project is focused on analyzing trade data of Italy from 2017 to 2022 to provide insights into the country's net trade. The goal is to present the data visually and provide valuable information regarding the Italian economy.

Video Game Recommendation System

A sophisticated recommendation system built to suggest video games based on multiple factors, utilizing the power of various similarity metrics

Western United States Power Grid Analysis

Analyzing the complex network modeling the Western United States power grid. Aiming to understand its structural vulnerabilities, increase resilience against unexpected disruptions, and ensure a more reliable and stable power grid.

Client Classification Using RF and LogR

This project focuses on classifying customers into distinct categories based on their behaviours and characteristics. Understanding and classifying customers into different segments in the modern business environment can significantly help marketing and improve customer service. This pipeline uses Random Forest and Logistic Regression to achieve this goal.

Current Location: Berlin, willing to relocate

Languages


Italian ●●●●●
English ●●●●●
German ●○○○○

Programming


Python ●●●●○
R ●●●●○
SQL ●●●○○
C# ●●○○○

Libraries and Software


Pandas, NumPy, Plotly, Seaborn, Matplotlib, Dash, SciPy, Sklearn, PyTorch, Spacy, Networkx, BeautifulSoup, Tableau, Unity, FMOD.
Basic knowledge of HTML and CSS

Academic CV

Gisma University of Applied Sciences
GPA 97/100

Undertaken courses: