I am a Freelance Big Data Scientist and Senior Software Developer.
Mainly focused on all aspects of data management such as Retrieval, Storage, Scaling, Analysis and Mining.
My usual data flow is Web Scraping, Relational Database, Cloud infrastructure, REST interface or Jupiter notebook, than Regression and Continuous Model deployment.
Always fascinated by the potential given intersecting data coming from the Web and Data Mining techniques such as Data Clustering,
Graph Analysis, Information Retrieval and Statistical Learning.
During my career, I also contributed on two scientific papers on the field of Web Scraping and Data Visualization.
Since 2019, together with a couple of friends we started Python Meetup Palermo, inspiring innovative ideas to a fertile local comunity. Regarding the location, Palermo is a place that I use to call the Italian Canary Islands, because of its permanent good climate and excellent high quality of living.
After many years of working experience with international clients, plus a Bachelor's and Master's degree, I decided to get back on Math and join the department of Statistics at University of Palermo.
I worked with Kiwi Campus on three months period, I joined them to help them out on the integration between their platform and Doordash Inc. I stumbled accross with Sasha Iatsenia, head of product at Kiwi Campus, even before he joined the company. We met some years before during a nomadic camp in Lanzarote, Canary Islands.
Everything started for fun working on an open source project I created in order to learn Python. The project was a Web Scraper using Selenium, which took a discrete amount of attention on github.com. In the meanwhile I started using Upwork in order to get remote jobs, and then I realized I could spend my earnings to travel and explore the world. So I started living as a digital nomad visiting countries such as: Belgium, The Netherlands, Germany, Czech Republic, Canary Islands, Spain, Romania, Switerland, Ireland, Italy. Then I moved for three months in Perù and one in Berkeley, United States.
During a year long internship at SpazioDati, I worked with Ugo Scaiella and prof. Paolo Ferragina, on the application of an Active Learning technique to efficiently select textual snippets to be annotated by humans. The dataset was created using the platform CrowdFlower (now re-branded as Figure Eight) and it was used to train a logistic regression model that replaced one of the steps of SpazioDati’s proprietary Entity Linking system (SaaS): namely Dandelion.
I graduated from Università di Pisa on a Bachelor's degree in Computer Science, then Master's degree in Data Science and Business Informatics. During my studies, I explored different research fields, including Information Retrieval, Natural Language Processing and Machine Learning. During those years I also worked on an European Research Project on Information Extraction. Thanks to Erasmus LLP Programme I had the chance to study at Universidad Politecnica de Valencia, Spain.