Case study

Transforming 264 Villages with Data

Overview

We partnered with M.P. Kesineni Srinivas and the Tata Trusts to create model villages throughout Vijayawada. To do this, we collected data from over 250,000 households in just 90 days, then helped officials use that data to target and plan their programs more effectively.

Partners

Tata Trusts

Kesineni Srinivas

Minister of Parliament, Vijayawada

Government of Andhra Pradesh

Centre for People's Forestry

Sectors

Government

Philanthropy

Nonprofit

264

villages covered

250,000

households surveyed

100 mil.

data points collected

1,200

surveyors trained

Watch how data-driven microplanning transformed 264 villages in Vijayawada, Andhra Pradesh

The Problem

Microplanning for 264 villages in Vijayawada, Andhra Pradesh

The Saansad Adarsh Gram Yojana, a rural development program launched in October 2014, required that every Minister of Parliament choose one village from their constituency and turn it into a model village by 2016.

Instead of choosing just one village, Mr. Kesineni Srinivas (MP of Vijayawada in Andhra Pradesh) partnered with the Tata Trusts and SocialCops to transform each of the 264 villages in his constituency. This joint program aimed to build a micro-targeted development plan for every individual, household, and village in Vijayawada in just 90 days.

The Solution

Using data intelligence for targeted, data-driven policies

The Tata Trusts partnered with us to help all levels of district officials plan for better budget and policy decisions in Vijayawada. We created a centralized planning tool for the constituency that was used to effectively micro-target development initiatives.

We trained first a team of surveyors, who used Collect (our mobile data collection app) to collect and map data for each household and each village’s infrastructure, healthcare facilities, schools, and more. Each of the 8 baseline surveys ranged from 76 to 117 questions.

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 prodiles, development indices, and priority scores. We then visualized this data in two interactive dashboards with geoclustering, household-level views, village profiles, and intelligent querying tools.

How we brought this dream project to life

1. Questionnaire creation
1. Questionnaire creation

Our data scientists created 8 household and village surveys with built-in validations to improve data quality.

2. Surveyor training
2. Surveyor training

We trained 1,200 volunteers from our partner organization on how to use a tablet and collect data.

3. Data collection
3. Data collection

Volunteers collected 150 data points from every household in Vijayawada — a total of 264 villages in 90 days.

4. Data flagging
4. Data flagging

As data was collected, it was automatically verified and bad data was flagged for re-collection.

5. Data analysis
5. Data analysis

Our data scientists processed, cleaned, and analyzed all the data to create village scorecards.

6. Data visualization
6. Data visualization

Data was visualized on two interactive dashboards with village profiles, geoclustering, and more.

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.

Poornima Dore

Senior Programme Manager

Tata Trusts
No internet required
Geotag each household
Reduce survey time with skip logic
Convert the app to Telugu

Data collection

  • Many parts of Vijayawada do not have mobile or internet service. Data was saved to tablets’ local storage, then synced when internet was available.

  • Every household was geotagged on a map using GPS, even without internet. Surveyors also used Collect to map village health centers, schools, and more.

  • Every survey was automatically customized with the most relevant questions for the person being surveyed. This saved crucial time on every survey.

  • Many surveyors only spoke Telugu, so the entire Collect app — including action buttons and instructions — was converted to Telugu.

Learn more about Collect

Automatic backchecks

As data was collected, it was automatically verified on Transform. Any data point that fell outside of pre-set parameters or was inconsistent was automatically flagged on Collect. Then surveyors could immediately return to check and re-collect that data point in the field.

Data transformation

1

Consistency checks

Included intra-variable (checking each variable for incorrect values) and inter-variable checks (ensuring that data is consistent across variables).

2

Village scorecard creation

Data was aggregated to score the development of each village, based on various individual, economic, health, and infrastructure development indicators.

3

Schemes matching

By matching eligibility data for each scheme with each person's data, we determined when people were not using schemes that they were eligible for.

Identify clusters for development
Query and identify focus areas
View comprehensive village profiles
View schemes coverage

Village-level dashboard

  • Mapping made it easy to find hidden patterns, such as the link between distance to the river and toilet use.

  • Decision makers could create queries like “villages with no bus stations and population > 5,000 people”.

  • All the data — healthcare, education, infrastructure and more — that officials needed was available through interactive charts.

  • We matched scheme eligibility data with individual data, so officials could understand how scheme eligibility varied.

Individual-level dashboard

By matching eligibility data for each scheme with each person's data, we determined when someone was not using schemes for which they were eligible. Local administrators used this dashboard to make sure every person received all of their scheme benefits.

1,200

volunteers trained

200

facilitators trained

500

tablets used

7

days of training

18

training sessions

100 mil.

data points collected

In October 2015, the Chief Minister of Andhra Pradesh, Chandrababu Naidu, and Mr. Ratan Tata launched the data-driven development plans created through this program.


Read more about the deployment:

With the launch of these 264 Village Development Plans for Vijayawada Parliamentary Constituency, we have redefined participative democracy and given our citizens real say in development. In this unprecedented effort, over 1 million people were mobilised for the creation of development plans. What we have achieved today is a big step in our mission to make Vijayawada a model constituency.

Shri Kesineni Srinivas
Shri Kesineni Srinivas

Member of Parliament

Vijayawada

DECK

Keep Reading

Want more information? Check out Slideshare for more details and the full story behind this case study.

Read more

At Atlan, we're opening up internal tools, like data catalogs, that helped us power massive data projects around the world.

Visit Atlan What Is a Data Catalog?