This document summarizes a presentation on using data for social good. It discusses several case studies where data and data science were used to help address social issues like homelessness, education access, and public health. Examples include using data to predict families at risk of eviction and homelessness in New York City, analyzing factors that contribute to successful online mentoring programs, and helping a land bank in Chicago prioritize properties for redevelopment. The presentation emphasizes bringing together different stakeholders like non-profits, technology companies, governments and community groups to tackle social problems through open data and collaboration.
17. Social Good
A good or service that benefits the largest
number of people in the largest possible way.
古典案例
乾淨空氣、清潔⽤用⽔水、教育、社福、⼈人權
現代案例
醫療、網路
相關概念
Common good, public service, corporate social responsibility
18. forBig Data Social Good
Data
Data Science
“Good people using data to do good things.”
⼀一個概念
27. Background
• 53,000 people in living in homeless shelters in New York during
November 2013, including over 12,000 families with over 22,000
children.
• Eviction is one of the top reasons families lose their homes and
transition into to the city’s shelter system.
Question
• What if we could predict which families are at heightened risk of
homelessness via eviction?
• Early warning -> early intervention
Early Results
• A tool that allows social workers and advocates to predict the likelihood
of an eviction notice leading to shelter entry, as well as the timeframe
available for prevention.
What’s Next
• Help NGOs use the prediction results to communicate with at-risk
families.
http://blog.sumall.org/post/88610177356/the-numbers-behind-the-words
32. Background
iCouldBe’s e-mentoring program has served over 19,000 at-risk youth
since 2000, providing middle and high school students with an online
community of professional mentors that empowers them to stay in school,
plan for future careers and achieve in life.
Question
• Need definitions for their organizational goals and metrics to improve
their program.
• “What makes a mentoring engagement successful?”
Early Results
• Defined a “successful” mentee/mentor engagement as one where a
mentee completes at least 3 “quests” or learning modules in 3 months.
• Identified the characteristics of engagements and interactions.
• "I'm here for you.”
• A Predictive model to identify key predictors
• A framework for text analysis
What’s Next
• Find more indicators of success/failure
• Review current programs
http://www.datakind.org/projects/uncovering-the-abcs-of-successful-online-mentoring/
36. Background
• The Cultural Data Project (CDP) not only collects financial and
programmatic data from over 11,000 arts and cultural institutions across
the U.S., it delivers that information back to the organizations
themselves, to the funders who support them and into the hands of
advocates and policy makers who believe in them.
• Each year, organizations ranging from small, all-volunteer dance
troupes to multi-million dollar museums across the country submit data
to CDP as part of the grant application process with public and private
funders. This means CDP has collected a broad dataset with 50,000
records, including up to 1,200 data points on each organization.
Question
• What makes an art organisation successful?
• How can we create more effective tools and training?
Early Results
• Found clusters of art organizations
• Compared the financial success of the five clusters that resulted from
the CDP Team's segmentation.
• “cluster-4,” is the one cluster that does not achieve financial success.
This cluster is a mixed cluster, not dominated by any one type of
organization.
What’s Next
• Improve the categorisation of art organizations
• Develop targeted services to organizations and enabling them to
benchmark themselves to understand how they’re doing in relation to
their peers.
http://www.datakind.org/projects/clustering-arts-organizations-to-help-them-thrive/
41. Background
• GlobalGiving is the world's first and largest crowdfunding community for
nonprofits. Since 2002, more than 400,000 donors have given $150
million to more than 10,500 projects in 160 countries.
• GlobalGiving also helps them learn fundraising and operational best
practices to improve their efficiency and increase their impact.
Question
• GlobalGiving wanted to help their community be even more successful
by looking at their past fundraising campaigns or “projects” to
determine what factors lead to projects being successfully funded.
• They wanted to know - was there a formula for project success?
Early Results
• Success factors: project title, funding amount, photos, speed of
funding?
• Projects focused on hunger did better than projects focused on
economic development and nearly 50% of donors skip the predefined
donation values, choosing instead to enter their own donation amount.
• A correlation between specificity of language and project success.
• “arts” < “photography exhibit"
What’s Next
• Take a deeper look at the data
• Improve data quality
http://www.datakind.org/projects/helping-great-causes-get-funded/
44. Background
• Boarded up buildings and overgrown lots have plagued Chicago’s low-
income neighborhoods for decades.
• Over the past five years, however, vacant and abandoned properties
have spread beyond the inner city and into the suburbs, disrupting
formerly stable working and middle class communities and prompting
the creation of a county-wide land bank, a new tool for fighting blight.
• Properties become vacant or abandoned because of weak real estate
markets in impoverished neighborhoods or because of the recent
region-wide foreclosure crisis.
Question
• The Cook County Land Bank has one job: to acquire vacant and
abandoned properties throughout Cook County and return them to
productive use.
• There are tens of thousands of boarded up homes and overgrown lots
in Cook County, and the land bank’s budget is limited.
• How will the agency figure out which of these properties to acquire, and
what to do with them?
Early Results
• A database to search and analyze vacant properties.
• A model to compare the quality of neighborhoods.
What’s Next
• Engage stakeholders in communities to come up with mutually
acceptable criteria.
• A clear, justifiable plan of action for putting vacant properties back to
work.
http://dssg.uchicago.edu/2014/01/20/cclb-real-estate-finder-for-vacants.html