Embed code
Note: this content has been automatically generated.
uh there will be the football world cup in russia and as perhaps you've noticed everyone who's interested in
football tries to predict the outcomes of the the matches and eventually the winner of the work
then there's also all the octopus a common octopus when two thousand and ten
successfully predicted eight out of eight games in the world cup including the final
so my friend victor and i uh we're big fans of football and we're also passionate about statistical models
so we ask ourselves the question can we mean to poll the octopus
as a starting point we took a popular model of match outcomes
uh which assumes that every team is correct tryst by scale so
based on previous outcomes of matches we can estimate this scale
now as players join and leave the teen this scale changes and so
in order to address that we had to develop a new method
so by using a a powerful machine learning technique called approximate basin inference
we were able to learn these time varying skills and improve decrease of the productions by ten to fifteen percent
as a picture is worth a thousand words i brought you this graph which shows the evolution of the scale
over years of the four teams that compose group e. of the
upcoming work out that's brazil switzerland costa rica in serbia
and as you can see here for example brazil is clearly the strongest teams of the four nowadays
but it's not as strong as it was in nineteen seventy when it had really golden generation of players
uh then switzer land a really improved over the last uh two decades or so
but it's still pretty close to serbian costa rica so those games are gonna be a pretty hard for
switzerland to win so finally we came up with a model that is fine tune for what got
and after a million simulations we found out that according to our model brazil is the
most likely team to win the world cup we twenty six percent chance it's
followed by spain and argentina but this also means that and there are three chances
out of forgot presumably not wind what got things looked darker for switch
we only have one point five chances of winning the world cup
but we have four point three seven chances reached a final
anyway we built the website one where you can access all our productions as
well as details about james such as the skills learned by the model
check out kickoff today i for more information please note that we cannot be held
accountable for any win or loss that you would enjoy using our system

Share this talk: 


Conference program

Welcome address
Andreas Mortensen, Vice President for Research, EPFL
7 June 2018 · 9:49 a.m.
Introduction
Jim Larus, Dean of IC School, EPFL
7 June 2018 · 10 a.m.
The Young Software Engineer’s Guide to Using Formal Methods
K. Rustan M. Leino, Amazon
7 June 2018 · 10:16 a.m.
Safely Disrupting Computer Networks with Software
Katerina Argyraki, EPFL
7 June 2018 · 11:25 a.m.
Short IC Research Presentation 3: kickoff.ai
Lucas Maystre, Victor Kristof, EPFL (LCA)
7 June 2018 · 12:19 p.m.
Short IC Research Presentation 5: CleanM
Stella Giannakopoulo, EPFL (DIAS)
7 June 2018 · 12:25 p.m.
Short IC Research Presentation 7: Datagrowth and application trends
Matthias Olma, EPFL (DIAS)
7 June 2018 · 12:31 p.m.
Short IC Research Presentation 8: Point Cloud, a new source of knowledge
Mirjana Pavlovic, EPFL (DIAS)
7 June 2018 · 12:34 p.m.
Short IC Research Presentation 9: To Click or not to Click?
Mahsa Taziki, EPFL (LPD)
7 June 2018 · 12:37 p.m.
Short IC Research Presentation 10: RaaSS Reliability as a Software Service
Maaz Mohiuddlin, LCA2, IC-EPFL
7 June 2018 · 12:40 p.m.
20s pitch 2: Gamification of Rehabilitation
Arzu Guneysu Ozgur, EPFL (CHILI)
7 June 2018 · 2:21 p.m.
20s pitch 4: Neural Network Guided Expression Transformation
Romain Edelmann, EPFL (LARA)
7 June 2018 · 2:21 p.m.
20s pitch 5: Unified, High Performance Data Cleaning
Stella Giannakopoulo, EPFL (DIAS)
7 June 2018 · 2:21 p.m.
20s pitch 6: Interactive Exploration of Urban Data with GPUs
Eleni Tzirita Zacharatou, EPFL (DIAS)
7 June 2018 · 2:22 p.m.
20s pitch 7: Interactive Data Exploration
Matthias Olma, EPFL (DIAS)
7 June 2018 · 2:22 p.m.
20s pitch 8: Efficient Point Cloud Processing
Mirjana Pavlovic, EPFL (DIAS)
7 June 2018 · 2:23 p.m.
20s pitch 9: To Click or not to Click?
Mahsa Taziki, EPFL (LPD)
7 June 2018 · 2:24 p.m.
20s pitch 10: RaaSS Reliability as a Software Service
Maaz Mohiuddlin, LCA2, IC-EPFL
7 June 2018 · 2:24 p.m.
20s pitch 11: Adversarial Machine Learning in Byzantium
El Mahdi El Mhamdi, EPFL (LPD)
7 June 2018 · 2:24 p.m.

Recommended talks

Keynote - Reproducibility and Open Science @ EPFL
Pierre Vandergheynst, EPFL VP for Education
24 March 2017 · 9:20 a.m.
Les technologies évoluent, comment les faire accepter?
Nicolas Henchoz, Directeur de l'EPFL-ECAL Lab
25 Aug. 2016 · 10:21 a.m.