Picture this: Every
January. Davos. World Economic Forum.
Most people would envision an exclusive gathering of the
world’s movers and shakers, some might see a big collection of private jets,
but since I’m a data analyst the only thing I can think of is… lots of
data. And I’m not disappointed.
Since 2006, the World Economic Forum has published the annual
Global Risks report which identifies risks that might cause significant
negative impact for several countries and industries. A key characteristic of global risks is their
potential systemic nature to affect an entire system, as opposed to individual
parts and components.
The risks can be viewed in terms of the financial impact
they might cause or the probable likelihood they might occur. The risks are also grouped into five
categories: (1) Economic, (2) Environmental,
(3) Geopolitical, (4) Societal, & (5) Technological.
The data was visualized as a bump chart. The viz reveals that economic risk dominated
from 2007 to 2014, such as asset-price bubble as top risk (during the Global Financial
Crisis 2007-2009) and fiscal crises as a result of constrained fiscal finances (immediate
post-crisis years 2010-2014).
In 2015, societal and geopolitical risks emerge as top risks
with water crises (prolonged drought), spread of infectious diseases (Ebola in
West Africa), and interstate conflict (rise of Islamic State) occupying the top
five risks. Also in 2015, water crises
becomes the number 1 global risk in terms of impact and its category is
changed from environmental to societal to reflect its potential enormous effect
to social stability.
Eigentaste is a collaborative filtering algorithm
to elicit real-valued user ratings on a common set of items and applies
principal component analysis (PCA) to the resulting dense subset of the ratings
matrix (Technical talk).
Eigentaste is a technology to deliver personalized jokes
catered to your own taste, imagine that! (Marketing talk).
Eigentaste was developed
by Professor Ken Goldberg and his team at the University of California, Berkeley. The technology has been implemented in Jester 5.0, an online joke system, to recommend new jokes to users based
on their ratings of the initial set. Here’re
the funniest jokes from Jester 5.0 based
on users’ highest rating.
Laugh more, live longer!
