Big Data and Apache Hadoop for Financial Services

How Big Data and Hadoop Help Financial Services Firms Manage Risk and Stay Competitive

Financial services organizations around the world are experiencing drastic change. The global financial crisis of 2008 resulted in the failing of scores of banks, which also impacted incomes, jobs, and wealth. As a result, financial institutions need to work hard to avoid the repeat of such a crisis.

Additionally, financial sector companies realize that in order to thrive in a market that has changed so dramatically, they need to be able to improve their operational efficiencies, detect fraud quicker and more accurately, model and manage their risk, and reduce customer churn. To accomplish this, financial services firms are turning to big data technologies and Hadoop to reduce risk, analyze fraud patterns, identify rogue traders, more precisely target their marketing campaigns based on customer segmentation, and improve customer satisfaction.


Financial Services Use Cases

Below are a few of the use cases that illustrate how big data and Hadoop are being integrated in the financial services industry, providing companies with insights into their operations, their customers, and their markets.

Fraud Detection

Flagging anomalous activities in real time can help prevent potential security attacks or fraud. The MapR Converged Data Platform gives banks the ability to build usage models of “normal” behavior from histories of consumer behavior, analyze incoming transactions against individual and aggregate purchasing histories and take appropriate action if the activity falls outside the confidence level of normal behavior. As more data is ingested, more precise models can be built so the system can more accurately separate the atypical but legitimate behavior from the suspicious activities.

Customer Segmentation Analysis
Banks can create a more meaningful and effective context for marketing to customers if they can define distinct categories, or “segments” in which each customer belongs. Often, these segments are defined based on demographic information, but the more cohesive and useful segments are also defined by customer behavior. Banks can define better customer segments by using the MapR Converged Data Platform to collect and analyze all of the data that they have about their customers, such as daily transaction data, interaction data from multiple customer touchpoints (e.g., online, call centers), home value data, and merchant records. Banks can then analyze these data sets to group customers into one or more segments based on their needs in terms of banking products and services, and plan their sales, promotion and marketing campaigns accordingly.

Customer Sentiment Analysis
The growing number of channels through which customers communicate has resulted in banks needing to understand what their customers are saying about their products and experiences in order to ensure customer satisfaction. Banks can use the MapR Converged Data Platform to analyze comments on social media or product review sites, enabling them to quickly respond to negative or positive comments. With this new insight, not only can banks respond to emerging problems in a timely manner but they can also more effectively connect with their customers and gain a better understanding of the types of banking products and services that customers find valuable.

Risk Aggregation
Big data techniques can be used to gather and process risk data in order to 1) satisfy risk reporting requirements, 2) measure financial performance against risk tolerance, and 3) slice and dice financial reports. The MapR Converged Data Platform can benefit risk managers as they can perform on-demand historical analysis of risk data as well as receive real-time alerts when limits are breached.

Counterparty Risk Analytics
Whenever a firm engages in a business transaction with another party, the risk of doing business with that party must be priced into the terms of the deal. Since calculating counterparty risk requires more than computing a formula, firms typically run long and complex “Monte Carlo simulations” to get a complete picture of risk exposure at many points in time in the future. These simulations require huge volumes of data, massive parallel compute power, and system reliability to ensure firms can continue with business operations with no downtime. The MapR Converged Data Platform provides the performance, scalability, reliability, and the easy access and delivery of data to drive the key components of a counterparty risk analytics system.

New Products and Services for Consumer Credit Card Holders
Making new products and services available to consumer card holders is an ongoing initiative for banks. Improved marketing campaigns and ads through effective targeting are required in order to deliver services to consumers and increase revenue for banks. The MapR Converged Data Platform is used to provide new products and services for consumers in real time at a leading credit card company. Advanced machine learning and statistical techniques are employed over data that is stored in a highly available Hadoop cluster. MapR gives the credit card company the ability to use machine learning techniques for multiple purposes, including fraud detection and recommendations.

Credit Risk Assessment
Due to the global financial crisis, there are now much more stringent rules for determining whether or not to give a customer a loan, so banks need more accurate ways to determine a person’s credit risk. A number of quantitative indicators are used for credit risk assessment and credit scoring. The MapR Converged Data Platform enables banks to pull in customer data on everything from deposit information to customer service emails to credit card purchase history in order to gain a holistic view of their customers. With the MapR Converged Data Platform, financial institutions now have the tools they need to construct an in-depth view of their customers so they can properly provide accurate credit scoring and analysis.

360-Degree Customer Service
To offer optimal customer service, financial services institutions need to analyze unstructured data about their customers (social media profiles, emails, calls, complaint logs, discussion forums, website interactions). By analyzing this data, firms gain a much deeper understanding of their customers’ needs, and can respond accordingly with the right products and services. Using the MapR Converged Data Platform financial institutions are able to consistently optimize each customer's experience when those customers interact with the firm.


Financial Services Customers

Zions Bank
Utah-based Zions Bank, a subsidiary of Zions Bancorporation that operates more than 500 offices and 600 ATMs in 10 western U.S. states, relies on MapR for a critical part of their security architecture. MapR helps Zions identify phishing activity in real time and minimize the impact. With MapR, Zions can store larger volumes of data for longer periods and can run more detailed analytics and forensics. MapR provides Zions with unsurpassed security features, ease of management and superior performance capabilities, which allow for a more efficient use of hardware and a better ROI.


Learn More
WHITEPAPER

Addressing Fraud and Privacy Issues in Hadoop for the Financial Services Industry
Download

SOLUTION BRIEF

Investment banks have been dealing with high velocity for a long time, but volume is a relatively new factor and emerging as the strongest driver for banks to look at big data and Apache™ Hadoop®.
Read

MAPR SANDBOX

Get started with MapR Sandbox, the fastest on-ramp to Hadoop
Download

EBOOK

The Hadoop Buyer’s Guide: Find out which Hadoop implementation is right for you
Download