6 / 12
Page 65
conferenceseries
.com
September 25-26, 2017 | Atlanta, USA
2
nd
World Congress on
Medical Sociology & Community Health
Volume 7, Issue 4 (Suppl)
J Community Med Health Educ, an open access journal
ISSN:2161-0711
Medical Sociology 2017
September 25-26, 2017
J Community Med Health Educ 2017, 7:4 (Suppl)
DOI: 10.4172/2161-0711-C1-028
BIG DATA PREDICTIVE ANALYTICS: HOW SMART COMMUNITIES BECOME HEALTHY
COMMUNITIES THROUGH BIG DATA INFORMED PUBLIC POLICY FORMULATION AND
IMPLEMENTATION
Michael W. Popejoy
a
a
Nova Science Publishers, USA
T
oward application by policy and program planners working within the nexus linking public administration and public health
in supporting sustainable, built, complex adaptive healthy communities; predictive big data analytics is a series of emerging
datascience methods by which critical connections are made and strengthened through the sharing and data mining of massive
quantities of data located across diverse public datasets. The days of studying and working in any one discipline or niche are quite
likely over; and, the polymath mind and related analytical techniques rules the process of future public policy planning in solving
social problems that impact the health and welfare of communities. Big data predictive analytical tools provides communities with the
power to make better informed decisions rather than relying on guesswork based on inadequate data access and analysis. Prediction
from the massive amount of existing data is empowering, but, not perfect; however, any real time driven prediction remains more
powerful and satisfying than merely relying on a public agency’s best guess. The concept of big data reflects the reality today that
massive amounts of data are stored in a variety of depositories; and, are awaiting download and analysis by public community
planners and others. Big data is characterized by volume, velocity, and variety. Volume is easy to understand. There is so much data
stored it is characterized as big or massive and it is now measured in zettabytes (bytes with 20 zeros following). Velocity is also a
characteristic since big data moves through the network with lightning speed. Further complicating how big data is downloaded
and analyzed is the almost infinite variety characterizing the type of data and its storage format as it arrives and is stored in various
massive databases under widely differing categories which makes data mining complicated. These characteristics have driven the
development of new statistical analysis tools capable of downloading massive amounts of data (volume) at high rates of speed as new
data arrives (velocity) thus providing real-time updates, and mines critical information regardless of how it is stored (variety) while
not drilling down to individual identities thus ensuring privacy. This revolution in data management and analysis has created a new
kind of professional; the data scientist who combines knowledge of computers with statistics and knowledge of the environment
of smart, healthy communities in the 21st century. The benefits are readily available; but, the trajectory and speed of progress are
accelerating in the direction of improved prediction in complex adaptive systems where once politically driven agency agenda specific
best guesses were the norm with potentially unacceptable failure rates and frequent misuse of scarce community resources invested
in a less than optimal direction.
dr_popejoy@hotmail.com