Title:
|
A Policy Driven Approach to Proactive Fraud Management in Financial Data Streams
|
Fraud management is a vital business operation for financial institutions towards
minimising the widespread effect of fraud upon customer service delivery, bottom
line operating expenditure and the organisation's brand image reputation. Rapidly
changing fraud patterns continue to demonstrate fraudster's ability to actively reengineer
their methods in response to ad-hoc security protocol deployments, and
highlights the distinct gap between the speed of transaction execution within
streaming financial data and corresponding fraud technology frameworks.
Despite extensive research into fraud detection techniques using knowledge
discovery techniques, a 'store now, query later' processing model simply no longer
satisfies the fraud alerting requirements of multi-channel financial service
platforms and financial institutions are migrating to increasingly proactive methods
of fraud detection through real-time evaluation of streaming data channels prior to
transaction completion. While this may reflect a simple shift of data processing
from 'post' to 'pre' data storage, fraud strategy deployment continues to rely upon.
the assembly of complex data processing architectures using low level application
programming interfaces and existing solutions continue to address fraud detection
upon a single channel, resulting in highly fragmented and disparate approaches to
financial fraud management for complete service channel coverage.
This thesis presents a policy based language and encompassing architecture
framework for facilitating the conceptual level expression and implementation of
proactive fraud controls within multi-channel financial service platforms. It is
demonstrated how a domain specific language can be used to abstract the financial
platform into a stream based information model to reduce implementation
complexity and deployment latencies through an innovative. policy mapping
architecture usable bY' both expert and non-expert users. Supporting components
are developed and integrated into the framework model towards providing a
comprehensive suite of assistive tools for underpinning a preventive and holistic
approach to financial fraud management. Presented research provides important
contributions related to policy driven system specification and maintenance within
both financial fraud management, and also the wider information systems domain.
|