H2O.ai Case Studies Solving Customer Churn with Machine Learning

Edit This Case Study Record

	Solving Customer Churn with Machine Learning H2O.ai

Solving Customer Churn with Machine Learning

H2O.ai

Technology Category	Analytics & Modeling - Machine Learning Analytics & Modeling - Predictive Analytics
Applicable Industries	Finance & Insurance
Applicable Functions	Sales & Marketing
Use Cases	Predictive Maintenance
Services	Data Science Services
Challenge	Paypal, a global payments platform, was facing a significant challenge with customer churn. The company's previous approach to identifying churn was based on specific time increments, marking a customer as churned if they hadn't used the platform within that period. However, this method was not fully accurate and impacted the effectiveness of Paypal's marketing efforts to win back customers. The company needed a more precise way to predict if and when a customer would churn and the reasons behind it. This information was crucial for the operational teams to develop new programs aimed at customer retention. Read More
About Customer	Paypal is a global payments platform operating in 203 markets. The company has 173 million active customer accounts and processed 4 billion payments in 2014. Paypal's revenue is primarily derived from service fees as a percentage of payments made through its platform. Therefore, the number of active customers directly impacts the company's revenue. Customer churn is a critical business metric for Paypal, and the company has been working to minimize churn through various marketing and product development programs. Read More
Solution	Paypal's Senior Data Scientist, Julian Bharadwaj, and his team developed a predictive model using H2O's powerful predictive modeling and machine learning capabilities. The team used transaction and behavioral variables as well as demographic data for customers who had churned. The models could be modified across multiple parameters and run multiple times very quickly, ensuring the validity of the output. Paypal now uses H2O on Hadoop to run a predictive modeling factory - large-scale, rapid modeling - that helps the company run more sophisticated and effective marketing programs to reduce churn. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Analytics & Modeling - Predictive Analytics

Applicable Industries

Finance & Insurance

Applicable Functions

Sales & Marketing

Use Cases

Predictive Maintenance

Services

Data Science Services

Challenge

Paypal, a global payments platform, was facing a significant challenge with customer churn. The company's previous approach to identifying churn was based on specific time increments, marking a customer as churned if they hadn't used the platform within that period. However, this method was not fully accurate and impacted the effectiveness of Paypal's marketing efforts to win back customers. The company needed a more precise way to predict if and when a customer would churn and the reasons behind it. This information was crucial for the operational teams to develop new programs aimed at customer retention.

About Customer

Paypal is a global payments platform operating in 203 markets. The company has 173 million active customer accounts and processed 4 billion payments in 2014. Paypal's revenue is primarily derived from service fees as a percentage of payments made through its platform. Therefore, the number of active customers directly impacts the company's revenue. Customer churn is a critical business metric for Paypal, and the company has been working to minimize churn through various marketing and product development programs.

Solution

Paypal's Senior Data Scientist, Julian Bharadwaj, and his team developed a predictive model using H2O's powerful predictive modeling and machine learning capabilities. The team used transaction and behavioral variables as well as demographic data for customers who had churned. The models could be modified across multiple parameters and run multiple times very quickly, ensuring the validity of the output. Paypal now uses H2O on Hadoop to run a predictive modeling factory - large-scale, rapid modeling - that helps the company run more sophisticated and effective marketing programs to reduce churn.

Impact #1	Improved churn metrics and accuracy of information delivered to both executive and operational teams.
Impact #2	Increased speed at which models could be run, giving teams immediately actionable data.
Impact #3	Created more sophisticated and effective programs to reduce churn built around the output of the H2O machine learning algorithms.

Impact #1

Improved churn metrics and accuracy of information delivered to both executive and operational teams.

Impact #2

Increased speed at which models could be run, giving teams immediately actionable data.

Impact #3

Created more sophisticated and effective programs to reduce churn built around the output of the H2O machine learning algorithms.

Benefit #1	Reduced modeling time from 6-7 hours to less than 30 minutes.
Benefit #2	Reduced scoring time on the entire customer base from 72 hours to significantly less.

Benefit #1

Reduced modeling time from 6-7 hours to less than 30 minutes.

Benefit #2

Reduced scoring time on the entire customer base from 72 hours to significantly less.

Download PDF Version

Overview

Solving Customer Churn with Machine Learning

Operational Impact

Quantitative Benefit