Pedro Balage

Staff Data Scientist @PandaDoc | Researcher at IT-Lisboa | LxMLS Organizer


I am Staff Data Scientist @PandaDoc. Previously, I occupied the positions of Director of Machine Learning @aisle 3, Lead NLP Engineer @DefinedCrowd and, Lead Data Scientist for Search & Discovery at Farfetch.

I am affiliated to the Instituto de Telecomunicações and co-organizer of the Lisbon Machine Learning School (LxMLS). It got my PhD on natural language processing from the University of São Paulo (Brazil) - NILC lab.

Most of my background and experience are in the fields of Natural Language Processing, Machine Learning and Deep Learning.

I live in the beautiful Lisbon - Portugal.


Oct 3, 2022 I joined PandaDoc as Staff Data Scientist!
Aug 1, 2022 I helped organize the 12th Lisbon Machine Learning School (LxMLS) at Instituto Superior Técnico (IST - UL).
Nov 1, 2021 I will be teaching the Deep Learning practical classes this term at Instituto Superior Técnico (IT-UL).
Oct 15, 2021 Check the slides I presented at the Future.Works Tech Conference on “Landing Your Dream Job as a Data Scientist”.
Jul 15, 2021 11th Lisbon Machine Learning School (LxMLS)
Aug 1, 2020 I just joined DefinedCrowd as a Lead NLP Engineer!
Apr 20, 2020 Farfetch’s Search and Rank teams presented at the virtual European Conference on Information Retrieval (ECIR2020). Watch the full presentations on Youtube.
Dec 10, 2019 I will be participating in the panel discusson on Graph Representation Theory in the Lisbon NeurIPS Meetup at 15 December.
Oct 20, 2019 I will be attending the DSPT Day in Porto on 25/26 October 2019. If you are interested in talking with me about Farfetch , please come and meet us there.
Oct 19, 2019 I gave a talk at Semana da Informática - FEUP - University of Porto on the topic “An Introduction to Natural Language Processing”. Slides are avaliable here and the code here .
Oct 15, 2019 Check the slides I presented at the Taxonomy Bootcamp London on “Improving search experience with a taxonomy in the fashion domain” .
Jun 18, 2019 Check out the slides and video from my talk on Berlin Buzzwords about “Why data-driven methods will shape the future of relevance search”.
Mar 30, 2019 I presented in a workshop organized by Porto.AI the topic “An Introduction to Natural Language Processing”. Both course material and slides are available.
Jan 19, 2019 I gave a talk at DSPT#47 Meetup on the topic “New advances in Graph Representations for Ecommerce Search”. Check our the slides