case study: socialcops + tata trusts in vijayawada
TRANSCRIPT
Data-Driven Planning
Using data intelligence to drive targeted development for 264 villages
with
Tata Trusts Lead Partner
MP Kesineni Srinivas,Government of Andhra Pradesh
Government Partners
Centre for People’s Forestry Implementation Partner
| case study
The Problem1
Microplanning for 264 villages in Vijayawada, Andhra Pradesh
The Saansad Adarsh Gram Yojana, a rural development program launched in October 2014, requires that every
Member of Parliament choose 1 village from their constituency and turn it into a model village by 2016.
Not signed up for employment scheme
Needs running water and electricity
Mr. Kesineni Srinivas (M.P. of Vijayawada) partnered with the Tata Trusts and SocialCops to transform all of the 264 villages in his constituency. The result was a joint program to build a micro-targeted development plan for every individual, household,
and village in Vijayawada.
Needs electricity
Toilet not functionalNot included in
food distribution
No toilet
This type of micro-planning generally takes 6 to 9 months.
9 months
We had just 90 days to plan for 264 villages. 90 days
Our Solution2
Using data intelligence for targeted, data-driven policies
The Tata Trusts partnered with SocialCops to help all levels of district officials plan for better budget and policy decisions in Vijayawada.
Our data intelligence platform was deployed to create a centralized planning tool for the constituency that would be used to effectively micro-target development initiatives.
Overview
1. The absence of unintended changes or errors in some data. Integrity implies that the data is an exact copy of some original version, e.g. that it has not been corrupted in the process of being written to, and read back from, a hard disk or during transmission via some communications channel.
data jack (ˈdadǝ jak) n.
1. A wall-mounted or desk-mounted connector (frequently a wide telephone-style 8-pin RJ-45 ) for connecting to data cabling in a building.
Data Intelligence
data intelligence (ˈdadǝ inˈtelǝjǝns) n.
1. The process of transforming all available data — collected from the ground up, sourced from external data sets, and extracted from elaborate internal systems — into intelligent insights that make the best decision crystal clear.
2. The only logical way to make a decision in the twenty-first century.
data link layer (ˈdadǝ lingk ˈlāər) n.
1. Layer two, the second lowest layer in the OSI seven layer model. The data link layer splits data into frames (see fragmentation ) for sending on the physical layer and receives acknowledgement frames. It performs error checking and re-transmits frames not received correctly. It provides an error-free virtual channel to the network layer. The data link layer is split into an upper sublayer, Logical Link Control (LLC), and a lower sublayer, Media Access Control (MAC). one-
Our Platform
brings the entire decision-making process to one place. It makes even the toughest decision faster and easier.
Access external data
Collect data from the ground up
Connect your internal data
Visualize data and find insights
Transform and clean data
• Geospatial analysis • KPI tracking • Geoquerying • Strategic planning
Our Platform
Our mobile data collection app was used to collect and map data for each household, as well as each village’s infrastructure,
healthcare facilities, schools, and more.
Every day, 5 to 10 thousand survey responses — with a total of 1.5 million data points — came in from the field. This data was cleaned, verified, and structured to build aggregate village
profiles, development indices, and priority scores.
The transformed data was visualized in interactive dashboards with geo-clustering, village-level comparisons, household-level
views, village profiles, and intelligent querying tools.
Collect
Visualize
Transform
Our Process
1 2 3 4
Survey app creation
Questionnaire creation
Surveyor training
Data collection
5 6 7
Data analysis
Data flagging
Data visualization
Households surveyed1,200Volunteers trained
250,000
2015Year of deployment
100 milData points collected
government, philanthropysectors involved
The Story3
100 million data points, 264 villages, and 1,200 surveyors
Our data scientists created 6 different surveys:
- Household survey - Anganwadi survey - Health facility survey - Village survey - Village mapping - School survey
Each of the 6 surveys ranged from 76 to 117 questions.
All of these surveys were created with complex skip logic and built-in validations to improve data quality.
1 2
Questionnaire Creation3 4 5 6 7
We used Collect’s web dashboard to create the questionnaires on our mobile app.
1 2
Survey App Creation3 4 5 6 7
No coding requiredOur simple drag-and-drop web editor can be used to create any kind of data collection app in no time.
Easy skip logic and validationsAn intuitive UI makes it easy to add infinite skip logics or complex data validations to improve data quality.
20 question typesChoosing from numerous types of questions — from simple types like subjective and multiple choice to more complex media, tabular, and location question types — makes it easy to build any questionnaire.
Collect
We conducted trainings on how to use a tablet and collect data for volunteers from our partner organization, the Centre for People’s Forestry.
Key stats:
- 1,200+ volunteers trained
- 200+ facilitators trained
- 500 tablets used
- 7 days of training
- 18 total training sessions
- 4 hours of basic tablet training
1 2
Surveyor Training3 4 5 6 7
Volunteers from our partner organization, the Centre for People’s Forestry, went to every household in Vijayawada to collect data on Collect.
Key stats:
- 264 villages in just 90 days
- 150+ data points per household
- 200+ additional data points per village
1 2
Data Collection3 4 5 6 7
Collect
No internet requiredMany parts of Vijayawada do not have mobile or internet service. Data collected offline was continuously saved to tablets’ local storage, then synced to central servers when internet was available.
Telugu language Many surveyors only spoke Telugu. The entire Collect app — including action buttons and instructions — was converted to Telugu language by simply changing the language setting.
Custom geotaggingEvery household was geotagged on a map using GPS, even without internet. Surveyors also used our mapping features to map the boundaries of households, schools, and village infrastructure on a satellite map.
1 2
Data Collection3 4 5 6 7
Gollapudi
Name of Village
Ambapuram
Paidurupadu
Rayanapadu
Shahabad
Vemavaram
Enikepadu
Nunna
Collect
As data was collected, it was automatically verified on Transform.
1 2
Data Flagging3 4 5 6 7
Transform
Automated data checksAny data point that deviated from pre-set parameters, fell outside the distribution for that variable, or was inconsistent with other collected data was automatically flagged.
In addition, Transform sent a daily flagging report to all stakeholders to track data quality.
Re-collecting data in real timeOnce a data point was flagged by Transform, it was automatically flagged in the Collect app as well. Then the relevant surveyor returned to verify or re-collect that data point in the field on Collect.
Once all the data was verified, it was processed, cleaned, and analyzed by our data scientists on Transform.
1 2
Data Analysis3 4 5 6 7
Transform
Consistency checksIncludes intra-variable checks (checking each variable for incorrect values) and inter-variable checks (ensuring that data across variables is consistent).
Schemes and individual matchingBy matching eligibility data for each scheme with each person’s data, Transform determined when people were not using schemes for which they were eligible.
Village scorecard creationData was aggregated to score the development of each village, based on various individual, economic, health, and infrastructure development indicators.
Using Visualize, all of the cleaned, verified data was visualized in an interactive dashboard with…
1 2
Data Visualization3 4 5 6 7
geoclustering
village-level comparisons
household-level views
village profiles
intelligent query tools
Visualize
1 2
Data Visualization3 4 5 6 7
Identify clusters for developmentVisualize
1 2
Data Visualization3 4 5 6 7
Zoom into every household or person
*This view is private and restricted to the relevant government officers.
Visualize
1 2
Data Visualization3 4 5 6 7
Query to identify focus geographies
number of bus stops = 0 x village population > 2,000 x
Visualize
1 2
Data Visualization3 4 5 6 7
View detailed village profilesVisualize
The Results4
Micro-targeting development to create a model constituency
The end result of our solution was a
centralized planning dashboard,
which district administrators and development organizations alike used to target and plan their budgets, policies, and
initiatives more effectively.
The government wanted to start a program to encourage villages to build and use toilets.
Their assumption: Villages without toilets are far from Vijayawada, so the problem must be awareness.
Their plan: Launch an awareness plan to convince rural village that building and using toilets is important.
Example #1
However, the data showed that villages with high toilets penetration follow the river. The real problem in Vijayawada is water supply, not awareness.
With this knowledge, the government was able to create a more effective plan to promote toilet use by providing adequate water supply in villages far from the river, rather than just promoting awareness.
Example #1
Krishna River
Cluster of villages with low toilet penetration
Let’s zoom in on a particular family.
In this family, the 16-year-old son has dropped out of school to work and earn money for his family.
Example #2
Name Gender Age Relation to Head of Household Education Livelihood
Banavathu Male 39 Self Not Literate Skilled wage worker
Mayuri Female 34 Spouse Not Literate Skilled wage worker
Jaya Female 17 Daughter Secondary —
Karthik Male 16 Son Middle Skilled wage worker
Akriti Female 14 Daughter Middle —
Family Details Schemes
*This view is private and restricted to the relevant government officers.*Names changed for privacy reasons
We sourced and cleaned eligibility data for every government scheme, then matched it with every family’s demographic and income data. This shows the schemes that each family is eligible for.
Example #2
Eligible For Scheme
Availing Scheme Scheme Name Scheme Details
Banavathu PDS (Public Distribution System) 15 kgs of grain per month
Karthik Pre-Matriculation Scholarship for Scheduled Caste Students
Day Scholars: 150 INR scholarship per month, 750 INR book and ad-hoc grant per year Hostellers: 350 INR scholarship per month, 1000 INR book and ad-hoc grant per year
Banavathu Integrated Disease Surveillance Project
Detection and treatment of leprosy, including disability prevention and medical rehabilitation
Jaya National Scheme of Incentives to Girls for Secondary School
3,000 INR payment available to 18-year-old girls who pass the 10th class examination
Family Details Schemes
*This view is private and restricted to the relevant government officers.*Names changed for privacy reasons
*This view is private and restricted to the relevant government officers.
This family doesn’t know they are available for lots of schemes. Just telling the family about these schemes will let the 16-year-old son return to school, and the family improve their livelihood, education, and health.
Example #2
Eligible For Scheme
Availing Scheme Scheme Name Scheme Details
Banavathu PDS (Public Distribution System) 15 kgs of grain per month
Karthik Pre-Matriculation Scholarship for Scheduled Caste Students
Day Scholars: 150 INR scholarship per month, 750 INR book and ad-hoc grant per year Hostellers: 350 INR scholarship per month, 1000 INR book and ad-hoc grant per year
Banavathu Integrated Disease Surveillance Project
Detection and treatment of leprosy, including disability prevention and medical rehabilitation
Jaya National Scheme of Incentives to Girls for Secondary School
3,000 INR payment available to 18-year-old girls who pass the 10th class examination
Family Details Schemes
*Names changed for privacy reasons
The dashboard also was useful to the private sector.
For example, a taxi company used the tool to find unemployed people with certain qualifications, then hired them as drivers.
Example #3
In October 2015, the Chief Minister of Andhra Pradesh, Chandrababu Naidu, and Mr. Ratan Tata launched data-
driven development plans created through this program.
One important player in creating a data-centric culture in government is the technology partner. That's the role
SocialCops has been playing, and it's a relationship we value a lot.
Once we decide what the goals of the survey are, the technology partner helps us host it on mobile devices,
manage the back end, analyze the data, and finally visualize it such that the decision maker can see
exactly what he needs to.
Poornima DoreSenior Program Manager,
Tata Trusts
Our Partners5
Tata TrustsTata Trusts is amongst India's oldest, non-sectarian philanthropic organisations that work in several areas of community development. Since its inception, Tata Trusts has played a pioneering role in transforming traditional ideas of philanthropy to make impactful sustainable change in the lives of the communities served. Through direct implementation, co-partnership strategies and grant making, the Trusts support and drive innovation in the areas of education; healthcare and nutrition; rural livelihoods; natural resources management; enhancing civil society and governance and media, arts, crafts and culture. Tata Trusts continue to be guided by the principles of its Founder, Jamsetji Tata and through his vision of proactive philanthropy, the Trusts catalyse societal development while ensuring that initiatives and interventions have a contemporary relevance to the nation. For more information please visit www.tatatrusts.org.
Lead Partner
Centre for People’s ForestryCPF is a civil society organisation that works for the rights and livelihoods of forest dependent communities with due regard to conservation. It believes that the claim to conservation, control and management of the forest resources belong to the forest dwelling and dependent communities and their livelihoods should be the primary concern of all forestry programs. For more information, please visit www.cpf.in.
Implementation Partner
Government of Andhra PradeshThe Government of Andhra Pradesh is the governing body for the state of Andhra Pradesh, India’s tenth-largest state with 49.4 million inhabitants (as of the 2011 Census). The Government provides governance, programs, and development support for villages across 13 districts over a total of 160,205 square kilometers.
MP Kesineni SrinivasKesineni Srinivas won the 2014 Indian general election as a Telugu Desam Party candidate. He was elected the Member of Parliament to the 16th Lok Sabha from Vijayawada (Lok Sabha constituency), Andhra Pradesh. Prime Minister Narendra Modi has lauded the efforts of MP Srinivas and partners in working toward the development of Vijayawada’s 264 villages.
Government Partner
Government Partner
About SocialCops6
Recognition We’ve garnered widespread support since our start in 2013.
2015 and 2016 “40 Under 40” list
- Forbes India: 2015 “30 Under 30” list - Forbes Asia: 2016 “30 Under 30” list
- Recognized as one of the top 10 emerging startups by Prime Minister Modi
- Selected as one of the 35 startups to visit Silicon Valley with Prime Minister Narendra Modi for the India-U.S. Startup Konnect in 2015
and more…- United Nations World Youth Summit Award - Global Social Entrepreneurship Competition - IBM/IEEE Smart Planet Challenge - Singapore International Foundation - Young Social Entrepreneurs - Aseanpreneurs Idea Canvas
Press and Media We’ve garnered widespread support since our start in 2013.
Data intelligence can be used to confront the world’s most critical problems and make a truly data-driven decision.Indian Management
Tracking data that solves problems is their mission.Economic Times
I am thrilled with the pioneering work that SocialCops is doing. We are limited only by our imagination in terms of how technology can address the challenges facing humanity.Manoj Menon, managing director (Southeast Asia) of Frost & Sullivan
SocialCops is taking big data in a direction that very few companies have been able to do: providing data and insights that can help solve real problems for most of the planet.Pankaj Jain, Partner at 500 Startups
Thank You!For more information or to request a demo of our platform, check out
wwww.socialcops.com.
[email protected] @Social_Cops