sap fraud management for insurance - sapevent.ch · sap fraud management – design & setup...

SAP Fraud Management for Insurance

© 2013 SAP AG. All rights reserved. 2

Legal Disclaimer

This presentation is not subject to your license agreement or any other

agreement with SAP. SAP has no obligation to pursue any course of

business outlined in this presentation or to develop or release any

functionality mentioned in this presentation. This presentation and

SAP's strategy and possible future developments are subject to

change and may be changed by SAP at any time for any reason

without notice. This document is provided without a warranty of any

kind, either express or implied, including but not limited to, the implied

warranties of merchantability, fitness for a particular purpose, or non-

infringement. SAP assumes no responsibility for errors or omissions in

this document, except if such damages were caused by SAP

intentionally or grossly negligent.


Industry Data Emphasizes the Opportunity for

Fraud Management Excellence

“Total cost in the US of insurance fraud (non-health)

is estimated to be more than $40 billion per year” (Source: Federal Bureau of Investigation, US)

“Insurance fraud has risen by 23% in the last 12

Month…. as a result, insurance fraud is estimated to

now cost £2.1 billion per year. ” (Source: Experian Fraud Report 2012)

“According to the Association of British Insurers, the

sector is detecting more than 2,500 fraudulent claims

worth £18 million every week”. (Source: Experian Fraud Report 2012)

Historical fraud detection methods identify only 10% of fraud cases. In combination with post-payment identification

only 5% of detected frauds are recovered.

Source: Accenture global claims study (3000 personnel interviews)

Fraud Investigation is time consuming


What Does This Mean for Your Business?

How can we identify fraud before the financial

damage has happened e.g. a claim is paid?

How can we improve the fraud investigation

efficiency?

How can we keep track with changing fraud

behaviors?

How can we reduce the false positive signals?

What is the best approach to automate the fraud

detection process and predict the likelihood of

fraud?

How do we manage to check all claims for fraud

but ensure fast claim processing?

How can we better fulfill compliance regulations?


SAP Fraud Management for Insurance Prevent. Detect. Investigate. Monitor.

SAP Fraud Management helps Insurance

companies to optimize their combined ratio

by identifying claim frauds and avoid

payments on illegitimate claim requests

Closed-loop Fraud Processing: Supporting the full cycle of Fraud Management enabling you to detect and

prevent claim fraud across multiple line of business with direct impact on your loss ratio.

Seamless Integration: Bi-directional integrated fraud processing to detect suspicious claims as early as possible

and real-time information flow to ensure focused and integrated investigation

Optimized Investigation: Intuitive functionality to support your fraud investigators process fraud alerts from first

fraud signal to final decision in the most efficient way.

Prevent Detect

Investigate Monitor

Powered by SAP HANA


Investigation

Detection

Prevention

Monitoring

Alert

Notification

Fraud Management A Closed-loop, Cross-Functional Process

Fraud

Pattern

Analysis

Claim Handling

& Settlement (*)

Inquire &

Analyze Investigation

Inte

gra

tio

n

Con

fig

ura

tio

n

Pla

tfo

rm

Evaluation &

Decision

Fraud Monitoring & Performance Optimization

From Claim Notification to Claim Closure

Define Rules

& Predictive

Models

Setup

Fraud Detection

Strategy

Calibration &

Simulation

Online

Detection

Mass

Detection

Fraud

Investigator

Business

Analyst CIO

Head of Claim

Management

Head of Fraud

Investigation

SA

P F

rau

d M

an

ag

em

en

t fo

r In

su

ran

ce

(*) Claim Handling & Settlement is ONE of the business processes

SAP Faud Mangement for Insurance can work with


Fraud Prevention Objectives, Issues, Capabilities, and Benefits

Hybrid combination of rules and

predictive methods to identify fraud

Business users are enabled to define

fraud detection strategies incl.

optimization based on weight factors

and thresholds

Real-time simulation and calibration of

fraud detection strategies

All data from different source (SAP and

non-SAP) can be

Determination of strategies detection

based on fine granular criteria

Unknown fraud patterns often not

identified

Time consuming process and high

effort to change existing rules

No system support to simulate impact

of detection methods

Pattern analysis and fraud rule testing

limited to sample data from only a few

data sources

Limited capabilities for LoB specific

fraud criteria

Identify unknown patterns and react

quickly on changing fraud behaviors

Reduced effort without IT-involvement

to set up and calibrate fraud detection

strategies

Transparent, real time information of

impact on new / changed strategies

No misinterpretations of fraud behaviors

due to sample data

Reduced false positive and streamlined

fraud detection

Issues Key business capabilities Benefits

Objective: Define high effective fraud strategies based all relevant data in an easy way without IT-Involvement

Best practice solution: Real time fraud pattern analysis and advanced, easy to use capabilities to set up hybrid

fraud detection strategies.


Fraud Prevention Detailed capabilities

High-speed pattern

analysis based on all

available data

Consolidated data from

SAP and non-SAP

sources within SAP

HANA

Pattern Analysis Predictive Analysis Fraud Detection

Strategy

3 2 1

Design mathematical

modes to predict

likelihood of fraud

Model design and the

data visualization

Drag-and-drop visual

interface for data

selection, preparation,

and processing

Broad visualization

capabilities

Combination of fraud

rules and predictive

analytical methods

Intuitive way of setting up


Define individual weight

factors and thresholds to

calculate risk score

Fine granular

determination of fraud

detection strategy

Simulation &

Calibration

4

Real-time simulation of

defined strategies to

reduce false positive

Optimize results of fraud

strategies with real-time

calibration

Capability to compare


for further optimization

Define fraud detection strategies in combination of rules and predictive analytical methods including real-time simulation and

calibration of these strategies.

Provides an intuitive, easy-to-use environment for designing predictive models and visualizing data, which allows to uncover

hidden and untapped fraud patterns including a broad range of data and model visualization capabilities to gain higher insight


SAP Fraud Management – Design & Setup Time How to detect fraud - it is your choice!

Expert

Knowledge

Database

Detection

Methods

Detection

Strategy Business

Process

Predictive Model

Creation & Training

Rule

Creation

Known

Patterns

Unknown

Patterns

Via SAP HANA Studio or

SAP Predictive Analysis Optional


SAP Fraud Management How to detect fraud - it is your choice!

Expert

Knowledge

Database

Fraud Detection

Strategy

Predictive Algorithm

Known

Patterns

Unknown

Patterns

External

Hint

Rule

Fraud

Detection

Alert

Alert

Alert

Data Analysis


Predictive Algorithm to identify unknown Fraud Patterns SAP Predictive Analysis


Visualization gains insight into unknown Fraud Patterns SAP Predictive Analysis

Parallel Coordinates

Scatter Plot


Unknown Patterns: Informed & adapted with Predictive Insights SAP Predictive Analysis

DecisionTree


Fraud Detection Strategy - Detection Methods SAP Fraud Management


Simulation & Calibration SAP Fraud Management


Fraud Detection Objectives, Issues, Capabilities, and Benefits

Online fraud detection at any point and

as often as needed within claim process

High-speed mass detection due to

HANA technology

Provide claim handler with fraud signals

while capturing data based on hybrid


Fully integrated bi-directional fraud

processing

Fraud situation often identified after

settlement of claim

No capabilities to check existing claims

with updated fraud strategies

Fraud detection based on claim

handlers experience; manual process to

overcome system boarders

Limited to no real-time process

integration into claim handling process

Identify fraud as early as possible -

before claims are further processed and

paid

Use online real-time detection or mass

detection without limitations

Early identification of potential fraud

situation to enable claim handler

gathering more data

Apply automated fraud detection to

reduce manual work, ensure re-scoring

due to claim changes and provide

results of investigation back as soon as

possible


Objective: Detect fraud situations as early and as precise as possible to avoid claims payments for fraudulent

cases without manual work Best practice solution: Integrated fraud detection with online & mass detection capabilities incl. transparent

scoring results and seamless process integration


Fraud Investigation Objectives, Issues, Capabilities, and Benefits

Up-to-date fraud scoring based on

hybrid fraud detection strategies

Full insight into all relevant information

at the fingertip

Advanced alert management

functionalities and capabilities

Calibration of existing fraud strategies

with weight factors and threshold to

reduce false positive

Fully integrated bi-directional fraud

processing

Significant work and effort spend on

non value cases

Time consuming data gathering due to

system boarders

High effort due to insufficient

investigation capabilities

High workload due to huge number of

false positive

Changed claim situation not visible for

Investigators

Increase investigator ROI by focusing

on high score / high value cases

Faster fraud processing to avoid

blocking a claim longer than needed

Improve investigator efficiency and

reduced fraud processing expenses

Improved accuracy of fraud detection

with reduced false positive and false

negative detections

Investigation always on up-to-date

information to avoid double work


Objective: Investigate on fraud cases with an environment for processing fraud cases more effective and efficiently.

Best practice solution: Closed loop fraud investigation processing, full insight into all relevant information, high-

speed in-memory analysis to identify fraudulent behaviors and advanced alert management capabilities


Fraud Investigation Detailed capabilities

Online and mass detection

fully integrated into Claim

process

Alert generation based on

individual thresholds

Automated coverage

referrals set based on

identified fraud signal

Risk score & Value based

prioritization of work list

Alert Notification Inquiry & Analyze Investigation

3 2 1

Integrated insight into all

relevant information such

as claim, claim history,

involved parties, …

Google-like search across

data sources

Explorative Analysis and

ad-hoc queries to gain

complete perspective of

situation

Network Analysis to

identify relationships and

networks

Fast and intuitive way to

capture of investigation

findings

Collaboration with external

investigators in the field

Comprehensive

Alert Management

capabilities

Evaluation &

Decision

4

Fast-Decision Support to

enable efficient fraud

investigation

Based on decision

capturing further claim

processing is being

triggered accordingly

Closed-loop fraud investigation processing to capture all findings of the fraud investigator up to the final

decision. Support streamlined processing due to full insight, high-speed in-memory analysis and social

network analysis to identify suspicious behaviors.


Alert Notification – Home Screen SAP Fraud Management


Alert Notification – Alert Worklist SAP Fraud Management


Inquiry & Analyze – Alert Detection Log SAP Fraud Management


Inquiry & Analyze – Claim Overview SAP Fraud Management


Inquiry & Analyze – Network Analysis SAP Fraud Management


Evaluation & Decision – Alert Documentation SAP Fraud Management


Evaluation & Decision – Alert Closure SAP Fraud Management


Fraud Monitoring & Optimization Objectives, Issues, Capabilities, and Benefits

Work and performance analysis incl.

operational reporting

Monitor and optimize quality of

investigation

Permanent analysis of results

including real-time calibration of

strategies

Poor control over team workload

and overdue fraud signals

Limited capabilities to measure fraud

investigation performance

No Insight into effectiveness of fraud

rules and strategies

Accurate, consistent and transparent

data for informed business decisions

- any time & anywhere

React immediately on changing

situation to improve efficiency

Optimized fraud strategies based on

real time data to react on changing

fraud behaviors


Objective: Real-time performance analytics and management reporting to make informed decisions and take

appropriate, timely action

Best practice solution: User-centric dashboards provide users on all level with accurate and consistent data


Ad-hoc Calibration Mobile Application

Lab Preview


Fraud Analytics … mobile as well!


IT & Technology Objectives, Issues, Capabilities, and Benefits

Highly integrated & configurable

solution based on flexible and

communication based open

standards

Scalable, component-based

standard application

Business users are enabled to

define fraud detection strategies incl.

optimization based on weight factors

and thresholds

High integration and maintenance

costs due to a multitude of diverse

functional systems

Hugh effort to keep track with ever

demanding requirements of

business units to address changes

in insurance fraud trends

Development and maintenance of

fraud strategies requires IT

involvement

Flexibility to configure the solution

based on specific business needs

integrated in your existing system

landscape

Implementation in a step wise

approach and adapt solution

depending on the business needs

Reduced effort without IT-

involvement to set up and calibrate



Objective: Respond rapidly to business needs while keeping costs under control

Best practice solution: Integrate one strategic and integrated closed-loop fraud solution across LoB´s for best

overall TCO


SAP Fraud Management for Insurance Prevent. Detect. Investigate. Monitor.

Prevent Detect

Investigate Monitor

Powered by SAP HANA

Closed-loop Fraud Processing Execute your fraud program with most comprehensive approach

Increase investigator´s effectiveness and efficiency

1

2

3

Enable real-time fraud management across your value chain

Seamless Integration

Optimized Investigation


No part of this publication may be reproduced or transmitted in any form or for any

purpose without the express permission of SAP AG. The information contained

herein may be changed without prior notice.

Some software products marketed by SAP AG and its distributors contain

proprietary software components of other software vendors.

Microsoft, Windows, Excel, Outlook, and PowerPoint are registered trademarks of

Microsoft Corporation.

IBM, DB2, DB2 Universal Database, System i, System i5, System p, System p5,

System x, System z, System z10, System z9, z10, z9, iSeries, pSeries, xSeries,

zSeries, eServer, z/VM, z/OS, i5/OS, S/390, OS/390, OS/400, AS/400, S/390

Parallel Enterprise Server, PowerVM, Power Architecture, POWER6+, POWER6,

POWER5+, POWER5, POWER, OpenPower, PowerPC, BatchPipes,

BladeCenter, System Storage, GPFS, HACMP, RETAIN, DB2 Connect, RACF,

Redbooks, OS/2, Parallel Sysplex, MVS/ESA, AIX, Intelligent Miner, WebSphere,

Netfinity, Tivoli and Informix are trademarks or registered trademarks of IBM

Corporation.

Linux is the registered trademark of Linus Torvalds in the U.S. and other

countries.

Adobe, the Adobe logo, Acrobat, PostScript, and Reader are either trademarks or

registered trademarks of Adobe Systems Incorporated in the United States and/or

other countries.

Oracle and Java are registered trademarks of Oracle and/or its affiliates.

UNIX, X/Open, OSF/1, and Motif are registered trademarks of the Open Group.

Citrix, ICA, Program Neighborhood, MetaFrame, WinFrame, VideoFrame, and

MultiWin are trademarks or registered trademarks of Citrix Systems, Inc.

HTML, XML, XHTML and W3C are trademarks or registered trademarks of W3C®,

World Wide Web Consortium, Massachusetts Institute of Technology.

© 2011 SAP AG. All rights reserved.

SAP, R/3, SAP NetWeaver, Duet, PartnerEdge, ByDesign, SAP BusinessObjects

Explorer, StreamWork, and other SAP products and services mentioned herein as

well as their respective logos are trademarks or registered trademarks of SAP AG

in Germany and other countries.

Business Objects and the Business Objects logo, BusinessObjects, Crystal

Reports, Crystal Decisions, Web Intelligence, Xcelsius, and other Business

Objects products and services mentioned herein as well as their respective logos

are trademarks or registered trademarks of Business Objects Software Ltd.

Business Objects is an

SAP company.

Sybase and Adaptive Server, iAnywhere, Sybase 365, SQL Anywhere, and other

Sybase products and services mentioned herein as well as their respective logos

are trademarks or registered trademarks of Sybase, Inc. Sybase is an SAP

company.

All other product and service names mentioned are the trademarks of their

respective companies. Data contained in this document serves informational

purposes only. National product specifications may vary.

The information in this document is proprietary to SAP. No part of this document

may be reproduced, copied, or transmitted in any form or for any purpose without

the express prior written permission of SAP AG.


Fraud Management – Architectural Overview

SAP HANA

SAP ERP

R

Tables, Views, Procedures

Non - SAP

Application Server ABAP

Fraud Management

Mobile

Native iPad App

Browser

Desktop UI

R R OData via SUP

R

R

BOBJ Data Services

SAP LT Replicator

Service


SAP Fraud Management – Design & Setup Time How to detect fraud - it is your choice!

Detection

Investigation

Create Alert

Create Alert manually (e.g. whistle blower)

Create Alert automatically via Detection

Online & Mass Detection

Capability for extensibility such as customer specific workflow, …

Assign Alert

“Pull” by Investigator

Assigned to Investigator by Fraud Dispatcher

Assigned automatically due to customer specific algorithms (based on

extensibility options)

Investigate Alert

Task Management

Case Management

Configurable Activities

Capability for extensibility such as customer specific workflow,..


Inquiry & Analyze – Conflict of Interests SAP Fraud Management

sap fraud management for insurance - sapevent.ch · sap fraud management – design & setup...

Documents