/*! * JT website, version 3.0.0. * Last update: November 2020. * All content is released under the open BY-NC-ND license * https://creativecommons.org/licenses/by-nc-nd/3.0/ */
Educated in several acronyms across the globe (UNISR, SFI, MIT), I was co-founder of Tooso.
Tooso was proudly serving A.I.-powered predictions to 150 million devices per year,
before being acquired by A.I. unicorn Coveo in 2019.
I am currently Coveo's Lead Scientist, shipping machine learning models to hundreds of companies and millions of users. When not busy building products, I'm explaining how A.I. applies to business use cases, promoting the release of datasets to the scientific community, and exploring a variety of research topics at the intersection of language, reasoning and learning.
In previous lives, I managed to do scienc-y things for a professional basketball team, simulate a pre-Columbian civilization and give an academic talk on videogames (among others improbable "achievements"). My work has been featured several times in the general press, and presented in international venues (including talks at WWW, ACL, RecSys, SIGIR, NeurIPS, etc.).
If you want to know more, you can always check out my TedX talk, read my outreach work, or skip through my publications. Remember to stay in touch through Linkedin, meet me at my next talk or just write me a message.
# STABLE BUT RELATIVELY UNTESTED STUFF
Some coding projects, often linked to verbose blog posts. Don't try this at home.
Medium & Public Talks
Unsolicited opinions about the meaning of life, the universe and everything (but mostly A.I. plus some data engineering).
* Something to read:
• a zero-maintenance, full-Paas data ingestion platform;
• how to explain big numbers with computers;
• an opinionated overview of the current A.I. landscape;
• how to personalize search with deep learning in 100 lines of code.
* Something to watch:
• does the future need us?;
• "Not all those who browse are lost": zero-shot personalization using deep architectures;
• A.I. with humans and for humans.
# DEPLOYED (AND PRACTICALLY FORGOTTEN)
Tooso was an A.I. company providing smart search and NLP capabilities to big retailers: as co-founder and CTO, I led our tech and data science roadmap.
Tooso was backed by the Alchemist, selected by CDL and named a "Gartner Cool Vendor". Coveo acquired Tooso in July 2019 to accelerate the development of cutting-edge NLP and AI technology for search applications.
The project pioneered data science applied to professional basketball in Italy and Europe (well, it was some time before Brad Pitt's movie). As lead data scientist, I oversaw the team that re-engineered Olimpia Milano workflow for the strategic analysis of basketball "play-by-play" data.
I led the first data analysis and data vizualization effort on Milan's public bike-sharing service (using Processing, Unfolding, Leaflet and TileMill). No bikers (and no bureaucrats) were harmed for the project.
Some academia stuff
I have been publishing and peer-reviewing papers in a bunch of fields (computer science, computational social sciences, agent-based models, cognitive sciences, urban studies, ontology, philosophy of A.I.); a selection from my recent work is below.
* Shopper Intent Prediction from Clickstream E‑Commerce Data with Minimal Browsing Information
* Shopping in the Multiverse: A Counterfactual Approach to In-Session Attribution
* How to Grow a (Product) Tree: Personalized Category Suggestions for eCommerce Type-Ahead
* The Embeddings That Came in From the Cold: Improving Vectors for New and Rare Products with Content-Based Inference
* Trust and Distrust in Contradictory Information Transmission
I'm also a very proud author of Cellular Automata on the Stanford Encyclopedia, which may well be "the most interesting website on the internet" (or not).
If you need some pre-print/free version of something I wrote/taught/presented, just drop me a line.