Bruno Lepri

Understanding and Rewiring Societies

Digital breadcrumbs

October 2013, ScientificAmerican.com 33

The DaTa-mathematics

annual salary of $153,000 Based on

social circle, likely to

repay a loan.

according to cell phone GPs data, walks 5.7 miles per day.

Recent shift in text-messaging pattern; new

girlfriendlikely.

travels a mile out of

way to work each day.

Web and phone records suggest dissatisfaction with physician.

search engine records indicate coming down with the flu.

Pregnant, but doesn¹t know it yet.

Purchases five cups of

coffee (usually starbucks)

per day

Driven The digital traces we leave behind each day reveal more about

us than we know. This could become a privacy nightmare—or it could

be the foundation of a healthier, more prosperous world!

Just applied for a seventh credit card.

!By Alex “Sandy” Pentland

SocieTy

Call Detail Records - Mobility: from cell towers we can reconstruct the movement

patterns of a community

- Social Interactions: from call and sms we can reconstruct social networks and interactions

- Economic Activities: monitoring airtime expenses is useful for detecting impacts of economic changes and crisis

social and spatial network diversity is strongly associated with IMD rank (measure of prosperity) (Eagle et al., 2010, Science)

Economic Development

Estimating Poverty Maps

!  Toole et al. show that it’s possible to observe mass layoffs and identify the users affected by them in mobile phone records

!  job loss has a systematic dampening effect on their social and mobility behaviour

Tracking Employment Shocks

Idea Flow and Unemployment

!  increased ratio of residents ---> more crime (in contrast with Newman’s thesis)

!  high diversity of functions (home vs. work) and high diversity of people (gender and age) act as eyes on street decreasing crime (in line with Jacobs’ thesis)

Predicting Crime Levels

How do you capture death & life of cities?

Some cities are alive, others less so ALIVE DEAD

DETROIT NEW YORK

The systematic acceleration of urban life

- Bettencourt, Luís MA, et al. "Growth, innovation, scaling, and the pace of life in cities." PNAS 104.17 (2007): 7301-7306. - Milgram, Stanley. "The experience of living in cities." Crowding and behavior 167 (1974): 41.

+ Social human-interactions

+ Economical GDP, wages, patents

-

Issues violent crimes, contagious diseases, pollution

The theory: Jane Jacobs

One of the most influential books in city planning

• Death: caused by the elimination of pedestrian activity

• Life: created by a vital urban fabric at all times of the day

Jacobs’ diversity conditions

Diversity => Urban vitality

There are 4 diversity conditions

To be ensured in each city’s district (10,000+ inhabitants)

SMALL BLOCKS LAND USE

AGED BUILDINGS DENSITY

Border Vacuums

• Patches of land dedicated to one single use

• They could be either bad and good:

• Parks are good for pedestrian activity • But they are exposed to criminality

and deprivation if not well managed (e.g. night)

LAND USE SMALL BLOCKS

AGED BUILDINGS DENSITY

VACUUMS

“Operationalize” Vitality MILAN

Jacobs’ theory holds and is still valid

URBAN METRICS

…But something is different

LAND USE SMALL BLOCKS

AGED BUILDINGS DENSITY

VACUUMS

Which place looks safer?

The theory: Broken Windows

• City mismanagement • Dirty places • Poor infrastructure

Lead to misbehavior => Crime

18

Wilson, James Q., and George L. Kelling. "Broken windows." Critical issues in policing: Contemporary readings (1982): 395-407.

The theory: Jane Jacobs + Oscar Newman

Two of the most influential books in city planning

• Lit streets • Street-facing windows • Physical demarcation private-

public

19

Klemek, C. (2011) ‘Dead or Alive at Fifty? Reading Jane Jacobs on her Golden Anniversary’ Dissent, Vol. 58, No. 2, 75–79.

Appearance and liveliness

SAFETY PERCEPTION LIVELINESS

Safety perception: MIT Place Pulse

21

1 2MULTI- MODAL APPROACH

Safety perception: aggregation

22

1 2MULTI- MODAL APPROACH

Liveliness: metrics

23

MILAN

MULTI- MODAL APPROACH 1 2

1

Link: regression

24

MULTI- MODAL APPROACH 2

SAFETY PERCEPTION LIVELINESS

Urban metric Beta coefficient % of women (from census) 0.001 Deprivation -0.005 Distance from the center -0.003 Safety appearance 0.020**

0.65

** p-value < 0.001; * p-value < 0.01;

Safety perception <-> women, young people

Safety perception <-> elements

26

Now that we have new tools to measure aesthetics, we can estimate its consequences

… to understand the relative value of improving

the aestetics of neighbourhoods

Planning Civic Systems

UN Data Revolution

The Tyranny of Data?

The dark side of data-driven decision-making for social good:

-  computational violations of privacy -  lack of transparency -  social exclusion and discrimination

The Tyranny of Data?

Requirements for positive disruption of data-driven policies:

-  user centric data ownership -  algorithmic accountability -  living labs to experiment data-driven policies

!  de Montjoye et al. (2013) study fifteen months of human mobility data for one and a half million individuals and find that human mobility traces are highly unique.

!  in a dataset where the location of an individual is specified hourly, and with a spatial resolution equal to that given by the carrier’s antennas, four spatio-temporal points are enough to uniquely identify 95% of the individuals.

Unique in the Crowd

The New Deal of Data

Right to:

-  possess -  control -  dispose

OPAL Project

Bring the algorithms to the data, don’t share the data itself!

Data Challenge Initiatives

!  Data for Development (D4D): Ivory Coast and Senegal

!  Datathon for Social Good: London Data

!  Telecom/Tim Italia Big Data Challenge

Thanks lepri@fbk.eu