下载PDF
H2O.ai > 实例探究 > Solving Customer Churn with Machine Learning
H2O.ai Logo

Solving Customer Churn with Machine Learning

技术
  • 分析与建模 - 机器学习
  • 分析与建模 - 预测分析
适用行业
  • 金融与保险
适用功能
  • 销售与市场营销
用例
  • 预测性维护
服务
  • 数据科学服务
挑战
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.
关于客户
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.
解决方案
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.
运营影响
  • Improved churn metrics and accuracy of information delivered to both executive and operational teams.
  • Increased speed at which models could be run, giving teams immediately actionable data.
  • Created more sophisticated and effective programs to reduce churn built around the output of the H2O machine learning algorithms.
数量效益
  • Reduced modeling time from 6-7 hours to less than 30 minutes.
  • Reduced scoring time on the entire customer base from 72 hours to significantly less.

相关案例.

联系我们

欢迎与我们交流!

* Required
* Required
* Required
* Invalid email address
提交此表单,即表示您同意 IoT ONE 可以与您联系并分享洞察和营销信息。
不,谢谢,我不想收到来自 IoT ONE 的任何营销电子邮件。
提交

Thank you for your message!
We will contact you soon.