Loading Events

« All Events

  • This event has passed.

Meetup #61 – The art of recommending or suggesting

25 September, 2019 @ 18:30 - 20:30

Detalhes

Feeling “watched” while you’re online? We might have two awesome people that will help you understand the “Big Brothers” of tech, recommendation and suggestion systems and realize that they are not so scary at all. And may we recommend you to come and bring a friend?

=== SCHEDULE ===

The preliminary agenda for the meetup is the following:
• 18:30-19:00: Welcome and get together
• 19:00-19:30: Talk 1: “DIY Recommender System” by João Gomes – Farfetch.
• 19:40-19:45: Group photo
• 19:45-20:15: Networking / Coffee Break
• 20:15-20:45: Talk 2: “Classy – A conversational aware Suggestion System” by Diogo Ferreira – University of Aveiro
• 20:50: Closing, hanging out and some beers
• 21:00: Dinner is optional but it might be an excellent opportunity for networking (https://doodle.com/poll/4ygcz5dge2kfqghw)

See you there!

Talk 1:
Title: DIY Recommender System
Abstract: The Recommendations problem is the quintessential Data Science problem (fight me). It’s simple enough to get started but complex enough to leave plenty of room for innovation. It’s easy to understand but hard to get right. And it’s both fun and extremely valuable. During this talk, we will build, piece by piece, our own recommender system. In python of course. Attention: there may or may not be live coding, depends on how willing the speaker is to risk his reputation on that particular day.

Short Bio: João Gomes Sousa is a Data Scientist at Farfetch. Since joining the company 4 years ago, he has helped design and build the in-house recommender system that provides personalized content for the whole platform. His hobbies include long walks on the beach and RSVP’ing “maybe” to meeting requests.

Talk 2:
Title: Classy – A conversational aware Suggestion System

Abstract: Over the last few years, pervasive systems have seen some interesting development. Nevertheless, human-human interaction can also take advantage of those systems by using their ability to perceive the surrounding environment.
CLASSY is a pervasive system that is aware of the conversational context and suggests information (a.k.a documents) potentially useful to the users, by using semantic and distance token information together with a Reinforcement Learning approach as a way to learn how to get better over the time.

Short Bio: Diogo Ferreira is an MSc student in Computer and Telematics Engineering, at Universidade of Aveiro.
In the past two years, he took his first steps in the Artificial Intelligence world and since then, it became his main area of interest, so he tries to do a lot of research by completing some online courses, reading papers and books and following notable people’s work in this area.
He is currently affiliated with the Instituto de Telecomunicações de Aveiro (IT Aveiro), where he is working as a Research Fellow on the Context-Aware applications field at the same time that he finishes his Master Thesis.
He also enjoys to tinker with sensors and to make some home automation projects, mainly just for the fun of building new things.

Details

Date:
25 September, 2019
Time:
18:30 - 20:30
Event Categories:
,
Event Tags:
,
Event Website

Organizer

DSPT
Email:
info@datascienceportugal.com
Organizer Website

Venue

PCI – Parque de Ciência e Inovação, S.A.
Via do Conhecimento
Ílhavo (Aveiro), 3830-352 Portugal
+ Google Map
Phone:
+351 234 092 496
Website:
www.creativesciencepark-aveiroregion.com