Case study

Using Data to Invest $8 Million in Indian Agriculture

Overview

The Bill and Melinda Gates Foundation decided to invest $8 million in initiatives for small and marginal farmers in India. They partnered with SocialCops to effectively target this investment using data intelligence.

Partner

Bill & Melinda Gates Foundation

Sector

Philanthropy

Locations

Bihar Odisha Uttar Pradesh India

$8 mil.

funding to invest

31

external data sources

209

total indicators

9

indices created

The Problem

Targeting $8 million to help India's small and marginal farmers

The Bill & Melinda Gates Foundation, the largest private foundation in the world, created an $8 million fund to aid small and marginal farmers in Bihar, Odisha, and Uttar Pradesh in India.

They wanted to use data to identify where they should invest to maximize their impact and focus on internal priorities (female empowerment, agricultural extension, nutrition, and more). However, agriculture data for India is scattered, inconsistent, and difficult to work with.

The Solution

Creating a complete data-driven picture of agriculture in India

The Gates Foundation partnered with SocialCops to create a data-driven way for teams at the Gates Foundation to target their investments. Our platform was deployed to aggregate data from public sources, clean and structure the data, and visualize the data in an intuitive, useful dashboard.

Collect

Data from 31 different public data sources — including difficult data on crop productivity, access to irrigation facilities, local infrastructure, soil conditions, and more — was sourced from our data repository.

Collect

The data was matched and aggregated in a single data set with our entity recognition engine, which recognizes and corrects errors and inconsistencies. The data set was then transformed into district-level indices on economic situation, crop productivity, female empowerment, nutrition, and more.

Collect

The data and indices were visualized on an interactive dashboard with geo-clustering, district-level comparisons, advanced geographic queries, and detailed drill downs.

Before we bridge the development gap, we needed to bridge the data gap.

Melinda Gates
Melinda Gates

Co-Chair

Bill & Melinda Gates Foundation

Our Deployment Strategy

1

Data aggregation

Data from 31 sources was compiled, covering 209 indicators in 9 layers (agricultural profile, crop productivity, nutrition, etc).

2

Data cleaning and score creation

Our data scientists cleaned and verified all the data, then converted each layer's data into a single score for easier comparison across districts.

3

Data visualization

Data was visualized on an interactive dashboard with state-level views, district comparisons, an intelligent query engine, and access to raw data.

209 Data Indicators in 9 Layers

Economic & Agricultural Profile

Crop Productivity & Coverage

Horticulture Productivity & Coverage

  • Total population
  • Population below the poverty line
  • Average family size
  • Average landholding size
  • Total agricultural workers
  • Percentage of cultivators
  • Percentage of laborers
  • Small and marginal landholdings
  • Total income
  • Consumption expenditure
  • Average debt
  • and more...
  • Wheat
  • Rice
  • Maize
  • Sugarcane
  • Arhar
  • Bajra
  • Barley
  • Groundnut
  • Guarseed
  • Moong
  • Mustard
  • and more...
  • Onion
  • Potato
  • Peas
  • Sweet potato
  • Beans
  • Pulses
  • Beans
  • Dry chilies
  • and more...

Financial Services

ICT & Infrastructure

Livestock Services

  • Households with bank accounts
  • MNREGA-linked accounts
  • Kisan credit card use
  • Credit limit
  • Post office accounts
  • and more...
  • Mechanical agriculture equipment
  • Mobile phone use
  • Landline use
  • Road length
  • Assured irrigation
  • Groundwater extraction devices
  • Fair price shops
  • Electric tubewells
  • Cooperative marketing centers
  • Electricity consumption
  • Diesel tubewells
  • and more...
  • Cattle
  • Buffaloes
  • Sheep
  • Goats
  • Pigs
  • Poultry
  • Livestock equipment
  • Veterinary centers
  • and more...

Nutrition

Women's Empowerment

Policy & Advocacy

  • Infant mortality rate
  • Maternal mortality rate
  • Wasting among children
  • Stunting among children
  • MUAC level for children
  • and more...
  • Female-headed households
  • Women's land ownership
  • Female cultivators
  • Women's agricultural equipment
  • Female literacy rate
  • and more...
  • Coverage of NFSM scheme
  • Food security (pulses)
  • Food security (rice)
  • Food security (wheat)
  • Food security (cereals)
  • and more...
Data from everywhere
Trustworthy data
Unified and merged data
Easy geographic comparisons
  • Data was sourced from PDF files, web pages, text files, images, and Excel files from the most obscure corners of the internet.

  • Every data set in our repository was cleaned, checked for completeness and accuracy, and prioritized based on its relevance.

  • Diverse data sets were brought together through complex entity recognition, consistency checks, and error flagging.

  • Transform's geocoding and geo-boundary features made it easy to triangulate and compare locations across different data sets.

Learn more
Zoom into any geography
Identify clusters for investment
Query and identify focus areas
  • Users could drill down from national to district-level data, query at any level, and download the results to Excel.

  • Geospatial mapping made it easy to identify geographic clusters, patterns, and insights that would have been impossible to see in a table.

  • Teams at the Gates Foundation could find focus geographies with queries like “top 50 districts based on female-headed rural households”.

Learn more

Make every data-driven investment easier with data intelligence.

Request a demo

DECK

Keep reading

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

Read more