Fraud Detection in Banking using Big Data By Madhu Malapaka [email protected] For ISACA, Hyderabad Chapter Date: 14 th Dec 2014 Wilshire Software Technologies Revised: 14 th Dec 2014 1
Dec 22, 2015
1
Fraud Detection in Banking using Big Data
ByMadhu [email protected]
For ISACA, Hyderabad ChapterDate: 14th Dec 2014
Wilshire Software Technologies
Revised: 14th Dec 2014
2
Agenda
Wilshire Software Technologies
Revised: 14th Dec 2014
• Common Banking Frauds• Fraud Fighting Activities• Enterprise Fraud Systems Diagnostic Anatomy• Big Data• Hadoop Ecosystem• Banks Data Source• Social Network Data Providers• Big Data Integration – Technology Stack• Reporting Tools
3
• A deception deliberately practiced in order to secure unfair or unlawful gain or causing loss to another party.
Wilshire Software Technologies
Revised: 14th Dec 2014
Fraud
4
• A bank is typically exposed to different types of frauds.
Wilshire Software Technologies
Revised: 14th Dec 2014
Common Banking Frauds
5
• Fraud fighting activities can be grouped into three primary categories:
Fraud Prevention - Proactive Fraud Detection - Reactive Fraud Investigation - Action
Wilshire Software Technologies
Revised: 14th Dec 2014
Fraud Fighting Activities
6Wilshire Software Technologies
Revised: 14th Dec 2014
Source: www.executiveboard.com
Enterprise Fraud Systems Diagnostic Anatomy
7
Policy
Data Collection
Data Logs
Banking
Servers
Data Analysis
Fraud Detection
Compliance
Legal Action
Business Process Change
Adopt New Technologies
Report Management
Users
ATMS
ONLINE
CREDIT
FRAUD
PREVENTION
FRAUD ACTIONS
External Data Feeds
FRAUD DETECTION
8
Policy
Data Collection
Data Logs
Banking
Servers
Data Analysis
Fraud Detection
Compliance
Legal Action
Business Process Change
Adopt New Technologies
Report Management
Users
ATMS
ONLINE
CREDIT
External Data Feeds
FRAUD DETECTION
FRAUD
PREVENTION
FraudMAP™
Reputation Manager 360
FRAUD ACTIONS
9
FRAUD
PREVENTION
Monitoring Account Holder Behavior• It is organized around different phases or aspects of the online
banking process.
10Wilshire Software Technologies
Revised: 14th Dec 2014
FRAUD
PREVENTION
11
Policy
Data Collection
Data Logs
Banking
Servers
Data Analysis
Fraud Detection
Compliance
Legal Action
Business Process Change
Adopt New Technologies
Report Management
Users
ATMS
ONLINE
CREDIT
External Data Feeds
FRAUD DETECTION
FRAUD
PREVENTION
FRAUD ACTIONS
12
How Banks can leverage Data Mining
capabilities of
Big Data for
Fraud Detection
Wilshire Software Technologies
Revised: 14th Dec 2014
13Wilshire Software Technologies
Revised: 14th Dec 2014
• Velocity Moves at very high rates (think sensor-driven systems). Valuable in its temporal, high velocity state.
• Volume Fast-moving data creates massive historical archives. Valuable for mining patterns, trends and relationships.
• Variety Structured (logs, business transactions). Semi-structured and unstructured.
BIG DATA
14Wilshire Software Technologies
Revised: 14th Dec 2014
Hadoop is a combination of :• HDFS Storage• MapReduce Computation
Hadoop Distributed File System (HDFS)• Distributed file system for redundant storage.• Designed to reliably store data on commodity hardware.
MapReduce• A programming model for distributed data processing.• A data processing primitives are functions: Mappers and Reducers.
BIG DATA BY HADOOP
15Wilshire Software Technologies
Revised: 21/10/2013
Hadoop Ecosystem
Pig• High-level data flow language.• Made of two components:
Data processing language Pig Latin (Pig Scripts). Compiler to translate Pig Latin to MapReduce.
Hive• Data Warehousing Layer on top of Hadoop.• Allows analysis and queries using SQL–like language.
Mahout• Scalable machine learning algorithms on top
of Hadoop.
16Wilshire Software Technologies
Revised: 14th Dec 2014
Sqoop• A tool to automate data transfer between
structured datastores and Hadoop.
Flume• Distributed data/log collection service.• Collects data/log from their sources and puts in
a centralized location for storage and processing.
Hadoop Ecosystem
17Wilshire Software Technologies
Revised: 14th Dec 2014
Hadoop Ecosystem
18Wilshire Software Technologies
Revised: 14th Dec 2014
Identify Data Sources• Consider what data sources you’ll need to take advantage of.
Existing data sources• This includes a wide variety of data, such as transactional data,
survey data, web logs, etc.
Purchased data sources• Does your organization use supplemental data, such as
demographics?• If not, consider social media and news stream would complement
your current data to create additional project value.
Banks Data Source
19Wilshire Software Technologies
Revised: 14th Dec 2014
Social Network Data Providers
• This data works as input data to build big-data and can integrate with Bank’s Customer data.
20
CRM/customer supportPOS/purchasesemail/documents/collab.BI & data warehousesystem & network logsweb logs/clickstreamgoogle analytics/omniturefacebook/twitter/yelp/foursquare/googleexperian/epsilon/acxiommobile devicessensorsproduct reviewsgoogle search results+ more
many terabytes of data,sometimes many
PETABYTES
Banks Internal and Purchased Data
Wilshire Software Technologies
Revised: 14th Dec 2014
BIG DATA
21Wilshire Software Technologies
Revised: 14th Dec 2014
Big Data Integration – Technology Stack
Wilshire Software Technologies
22
Data Logs
RDBMS
Analytics
23Wilshire Software Technologies
Revised: 21/10/2013
Reporting Tools
24
81% of global bankssay Big Data is a top priority in 2015
Are You Ready?
Wilshire Software Technologies
Revised: 14th Dec 2014
25
Thank You!
• Questions?
Wilshire Software Technologies, based in Hyderabad, India is engaged in Consulting & Training for Big Data Analytics.
Contact Information:
Madhu MalapakaManaging DirectorWilshire Software TechnologiesHyderabad, IndiaCell +91 800 820 [email protected]
www.wilshiresoft.com
Wilshire Software Technologies
Revised: 14th Dec 2014