FOURTH EDITION DIVERS LIST
/ CHIARA BARBAGIANNI
/ SIMONE BASSO
/ ROBERTO CATINI
/ ANDREA CORRADI
/ HAI DAO
/ ISABELLA DAVID
/ ENRICO DEUSEBIO
/ ANDREA FAVENZA
/ JOSE ALBERTO GUIJARRO
/ LIONEL JOHNNES
/ ADAM KLIMONT
/ LORENZO MALANGA
/ ANDREA MARCHINI
/ GIORGIO MELON
/ MASSIMO MENICHINELLI
/ GIANLUCA MORETTO
/ ELENA OSTI
/ GIANNI ROSA GALLINA
/ TOBIAS SHOLL
TEACHERS & SPEAKERS
# Data Science
Andrè Panisson, Laetitia Gauvin and Michele Tizzoni – isi.it
Bruno Gonçalves – bgoncalves.com
Vittorio DiTomaso – celi.it
Vasil Tabaku – iconsulting.biz
Paola Pasino – ubdc.ac.uk
# Legal aspects of BIG DATA
Alessandro Mantelero and Federico Morando – nexa.polito.it
Team Group: C. Barbagianni, S. Basso, A. Corradi, A. Klimont, E. Osti
Team Composition: Developer: x1 | Designer: x1 | DataScientist: x1 | Linguist: x1 | Analyst: x1
Dataset by: Dimar
The analysis (based on standard deviation and confidence intervals, predictive models and network approach to pattern analysis) investigated if there are any features that allow for distinguishing and classifying stores in groups/clusters.
Team Group: E. Deusebio, L. Johnnes, A. Marchini, M. Menichinelli
Team Composition: DataScientist: x1 | Designer: x1 | NetworkArchitect: X1 | Marketing: X1
Dataset by: deltatre
Divers team defined two different sub-projects:
A) The first one was a kind of predictive analysis. Particularly 2 models were investigated
A.1 A predictive model that aims at anticipating the highlights in the football match.
A.2. A model that would help the tracking system to prevent errors in tracking of the ball or of the players.
B) The second was a study of the match like a Social Network. A web dashboard has been developed as final output. This dashboard might help managers or coaches to deepen why one of the team was so superior to the other in the match studied.
Team Group: R. Catini, I. David, A. Favenza, G.E. Melon
Team Composition: DataScientists: x3 | Researcher: x1
Dataset by: Sellalab and Consel
As online commerce becomes more common, fraud is an increasingly important concern. Automatic detection of hidden frauds, which elude standard control process, is needed in order to evolve the standard detection model.
Challenges was to decrease the human effort and achieving “optimal” trade-off of total cost (Total cost = Oppurtunity loss + Operation cost + Fraud loss).
Team Group: H. Dao, J.A. Garcìa, L. Malanga, G. Rosa Gallina, T. Scholl
Team Composition: Developer: x1 | DataScientist: x1 | Designer: x1 | Geographer: x1 | NetworkSpecialist: x1
Dataset by: Tierra
The team decided to set two main goals: first, understanding how to spot general patterns between errors and a set of device’s characteristics, including instrument model, position and how it was used; second, by retrieving only usage information over a common time reference (one month), predicting whether the device would have shown at least one error.