While Western Union’s business model has shifted over the years—from connecting customers through communications to connecting them financially through cross-border, consumer-to-consumer money transfers, bill payments, and other financial services—one fundamental underpinning has remained unchanged: a dedication to customer-centricity and connecting people with each other.
“One of the factors driving transformation for Western Union right now is the massive amount of transactional information that we accumulate as we serve our customers,” noted Sanjay Saraf, the company’s chief technology officer and senior vice president. “We’ve built an enterprise data hub on Cloudera to drive actionable insights that help the company create products and services that are relevant to our customers and help differentiate Western Union in a competitive marketplace.”
Western Union’s enterprise data hub (EDH) feeds in structured data from multiple data warehouses as well as unstructured data including click streams, behavioral data, logs, and sentiment data collected by tools such as transactional, marketing, and other outreach systems. Western Union uses a combination of Apache Flume, Apache Sqoop, and Informatica Big Data Edition (BDE) to collect data from the various sources. At the backbone of Western Union’s EDH are high-density Cisco Unified Computing System (UCS) servers.
Impact: 360-Degree Customer View
The data hub serves as a single repository to help Western Union know its customers, providing important insights from initial touch point and qualification and compliance checks, through their lifecycle. It allows the company to deliver push offers that are relevant and meaningful. It’s a customer-centric approach that helps Western Union offer targeted experiences for customers.
One insight revealed by the Cloudera hub was that many web and mobile customers frequently process repeat transactions—they send the same amount of money to the same recipient at the same time each month. This data prompted Western Union to add a “Send Again” button to make the process of repeating payments much more convenient for the customer.
- 99% of all queries execute in 15 minutes or less, with a median execution time of just 23 seconds.
- Queries on hundreds of thousands of units execute two orders of magnitude faster than before.
- Data reloads at a rate of three months per day, whereas it used to take a full day to reload 1.5 days’ data—that’s 60X faster.
“We’ve clearly seen that by deploying that capability, we immediately saw conversion uptake in those key sectors,” said Sanjay Saraf, CTO and Senior Vice President at Western Union.
Impact: Risk Management & Compliance
The EDH delivered immediate value to Western Union by supporting predictive analysis on structured and unstructured data sets in the same store, at the time of transaction. “We were able to, in real time, impact transactions and drive customer compliance in a way that drove better conversions for our customers,” said Saraf.
Impact: Machine Learning Reduces Fraud
Get the details on Western Union's multi-prong approach to countering fraud with machine learning in the Datanami article, “Western Union Clamps Down on Fraud with ML.”