DataRobot Case Studies Kiva Uses DataRobot to Increase Microloan Funding Rate

Edit This Case Study Record

	Kiva Uses DataRobot to Increase Microloan Funding Rate DataRobot

Kiva Uses DataRobot to Increase Microloan Funding Rate

DataRobot

Technology Category	Analytics & Modeling - Machine Learning
Applicable Industries	Finance & Insurance
Applicable Functions	Business Operation
Services	Data Science Services
Challenge	Kiva is a financial services nonprofit that uses crowdfunding to underwrite loans for people who are underserved by traditional channels. The World Bank estimates that approximately 1.7 billion people are unbanked, meaning they do not have access to financial services offered by retail banks. This leaves many people without access to the financial instruments that much of the world takes for granted, such as credit cards and loans. Alternative banking methods tend to have high fees that can put them out of reach for the people that need them. This lack of capital hinders economic growth, opportunity, and equality in the places that need it the most. The key to Kiva’s mission is to ensure that those who apply for loans are successfully funded. Read More
About Customer	Kiva is an international nonprofit founded in 2005, with a mission to “expand financial access to help underserved communities thrive.” Kiva accomplishes its mission by offering crowdfunded loans through its international network. The loans are used in various ways such as helping women start and grow their businesses, enabling farmers to purchase equipment, and providing students with loans to further their education. The organization is based in San Francisco, CA and operates in the nonprofit and financial services industry. Read More
Solution	With the goal of ensuring successful funding for loan applicants, Kiva partnered with the DataRobot AI for Good program to develop a system to promote loans that aren’t being viewed and are at risk of going unfunded. Using data about each loan, including daily popularity, the Kiva team used DataRobot to build more than two dozen models that predict which loans will be funded each day. This solution is built to integrate directly with the Kiva website, reordering the loans daily in a way that provides visibility to any that are at risk. The solution resulted in the promotion of loans in geographically diverse regions including parts of the world that are sometimes overlooked by funders. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Applicable Industries

Finance & Insurance

Applicable Functions

Business Operation

Services

Data Science Services

Challenge

Kiva is a financial services nonprofit that uses crowdfunding to underwrite loans for people who are underserved by traditional channels. The World Bank estimates that approximately 1.7 billion people are unbanked, meaning they do not have access to financial services offered by retail banks. This leaves many people without access to the financial instruments that much of the world takes for granted, such as credit cards and loans. Alternative banking methods tend to have high fees that can put them out of reach for the people that need them. This lack of capital hinders economic growth, opportunity, and equality in the places that need it the most. The key to Kiva’s mission is to ensure that those who apply for loans are successfully funded.

About Customer

Kiva is an international nonprofit founded in 2005, with a mission to “expand financial access to help underserved communities thrive.” Kiva accomplishes its mission by offering crowdfunded loans through its international network. The loans are used in various ways such as helping women start and grow their businesses, enabling farmers to purchase equipment, and providing students with loans to further their education. The organization is based in San Francisco, CA and operates in the nonprofit and financial services industry.

Solution

With the goal of ensuring successful funding for loan applicants, Kiva partnered with the DataRobot AI for Good program to develop a system to promote loans that aren’t being viewed and are at risk of going unfunded. Using data about each loan, including daily popularity, the Kiva team used DataRobot to build more than two dozen models that predict which loans will be funded each day. This solution is built to integrate directly with the Kiva website, reordering the loans daily in a way that provides visibility to any that are at risk. The solution resulted in the promotion of loans in geographically diverse regions including parts of the world that are sometimes overlooked by funders.

Impact #1	The solution integrated directly with the Kiva website, reordering the loans daily to provide visibility to any that are at risk.
Impact #2	The solution promoted loans in geographically diverse regions including parts of the world that are sometimes overlooked by funders.
Impact #3	This solution is the first large-scale machine learning model implemented by Kiva for this problem.

Impact #1

The solution integrated directly with the Kiva website, reordering the loans daily to provide visibility to any that are at risk.

Impact #2

The solution promoted loans in geographically diverse regions including parts of the world that are sometimes overlooked by funders.

Impact #3

This solution is the first large-scale machine learning model implemented by Kiva for this problem.

Download PDF Version

Overview

Kiva Uses DataRobot to Increase Microloan Funding Rate

Operational Impact