Hi! I'm Eugenia!

I am a Data Scientist with experience in both industry and research. I am particularly interested in geospatial data analysis and machine learning interpretability.

Project Portfolio

How to build a Shazam-like Telegram Bot using Python

Topic Modeling for E-commerce Reviews using BERTopic

GANomaly with Pytorch on MVTec dataset

Building a Web Application to detect Breast Cancer in Ultrasound images

An End to End Web App to detect anomalies from ECG signals with Streamlit

Deep Q-network with Pytorch and Gym to solve the Acrobot game

Articles

A Practical Introduction to Geospatial Data Analysis using QGIS

How to create a strong Data Science Portfolio for free

How to deploy your ML model using DagsHub+MLflow+AWS Lambda

A Comprehensive Guide to Image Augmentation using Pytorch

An introduction to Probability Sampling Methods

My Pandas Cheatsheet for Exploratory Analysis and Data Manipulation

Education

Master's Degree in Data Science at Università degli Studi di Padova

2019-2021

Bachelor's Degree in Statistics at Università degli Studi di Padova

2015-2019

Erasmus Student in Lisbon School of Economics and Management (ISEG)

February 2018 - July 2018

Work Experience

Data Scientist at CRIF

December 2022 - Present

Working on an automated valuation model for residential real estate and on other problems related to finance, insurance and geospatial data analysis.

Research Fellow at the Department of Information Engineering of University of Padova

October 2021 - October 2022

Anomaly Detection for Industry machinery. The research is focused on continual learning combined with anomaly detection.

Statwolf Data Scientist intern

March 2021 - June 2021

Created an anomaly detection System able to identify automatically abnormal behaviors of the compacting machine. The isolation forest combined with three intepretability techniques, SHAP, AcME and DIFFI, were used to detect and interpret the potential root causes of the anomalies.