Taking Data Analytics to the Next Level · Taking Data Analytics to the Next Level ... M&A due...
Transcript of Taking Data Analytics to the Next Level · Taking Data Analytics to the Next Level ... M&A due...
®2013 Association of Certified Fraud Examiners, Inc.
Taking Data Analytics
to the Next Level
The New Structured Toolbox:
Risk Scoring and Leading Analytics
®2013 Association of Certified Fraud Examiners, Inc.
2 of 31
Today’s Agenda
Section 1: 70 minutes
Key concepts in forensic data analytics
Technical baseline
Break: 15 minutes
Section 2: 70 minutes
Advanced forensic analytics using structured data
Advanced forensic analytics using unstructured data
Break: 15 minutes
Section 3: 70 minutes
Bringing it all together with big data
®2013 Association of Certified Fraud Examiners, Inc.
3 of 31
Introductions and Course Objectives
What would you like to take away
from this course?
Discussion…
®2013 Association of Certified Fraud Examiners, Inc.
4 of 31
Reflecting on the Fraud Triangle The fraud triangle is a key element to every test we design.
Internal
Controls
Internal and External
Pressure
Increased
mediums of
communication
Race to expand
in emerging
markets
Opportunity to
Commit Fraud
Budgets are
decreasing.
Companies and
organizations are
doing more with
less
Companies are
downsizing and
decentralized,
which has an
immediate effect
on internal
controls
Stressed and
dissatisfied
employees might
have greater
ability to
rationalize
improper actions
Pressure
Opportunity
Rationalization
Significant
company
expansion into
emerging
markets (BRIC
countries)
Job stress
is high
®2013 Association of Certified Fraud Examiners, Inc.
5 of 31
Need for Integrating Analytics
Bribery and corruption remain top risks Aggressive enforcement continues
New U.S. DoJ/SEC guidance
Risk areas: Integrity of sales force
Integrity of suppliers and distributors
Integrity of employees, conflicts of interests
Improper payments in the forms of bribes/kickbacks
Travel & entertainment abuse
M&A due diligence
®2013 Association of Certified Fraud Examiners, Inc.
6 of 31
Fraud Tree
Cash larceny
Theft of other
assets – inventory/
AR/ fixed assets
Revenue recognition
Non financial
Conflicts of
interest
Bribery and corruption/
FCPA
Illegal gratuities
Bid-rigging/ procurement
Corruption Fraudulent Statements
Asset Misappropriation
Fake vendor
Payroll fraud
T&E fraud
Theft of data
GAAP Reserves
General focus of auditors
General focus of
internal auditors
General focus of attorneys (opportunity for internal auditors and
investigators)
Starting with the Fraud Tree
®2013 Association of Certified Fraud Examiners, Inc.
7 of 31
ACFE’s 2012 Report to the Nations on
Occupational Fraud and Abuse
Estimated 5% of revenues lost fraud
Median loss per incident was $140,000
Median fraud duration was 18 months
before detection
More than 50% of cases reported globally were
corruption and billing schemes
The presence of anti-fraud controls is notably
correlated with significant decreases in the cost
and duration of the scheme
®2013 Association of Certified Fraud Examiners, Inc.
8 of 31
372 global CFOs surveyed
2012 Ernst & Young Global Fraud Survey
39% of respondents say that bribery &
corruption practices occur frequently in their
countries
15% of CFOs surveyed said they would be
willing to make cash payments to win business
20% of CFOs surveyed said that they
are willing to make personal gifts to
win business
®2013 Association of Certified Fraud Examiners, Inc.
9 of 31
How Companies Are Responding
Compliance and legal are looking beyond
policies and training Teaming with internal audit and internal investigations to test for
effectiveness
Integrating new analytics specifically targeting
corruption—these aren’t your typical process
controls or SOX testing
®2013 Association of Certified Fraud Examiners, Inc.
10 of 31
How Companies Are Responding
Developing “big data” concepts including: Text mining (unstructured data)
Statistical analysis and anomaly detection
Visual analytics and interactive dashboards
100% data sampling, not just random sampling
Analytics used as “pre-field work” before the on-
site audit or interview
®2013 Association of Certified Fraud Examiners, Inc.
11 of 31
Elements of
a successful
corporate
anti-fraud,
bribery and
corruption
program
Anti-fraud,
bribery and
corruption
key activities
may
include
►Review of fraud policies
and controls
►Industry benchmark of
anti-fraud programs
►Gap analysis
►Future state design
session
►Assess roles and
responsibilities
►Fraud and risk
committee formulation
►Customized training
►Corporate governance
►Corporate anti-fraud
road map
►FCPA / anti-bribery
assessments
►Fraud risk assessment
►Targeted anti-fraud analytics
►Anti-bribery and corruption
analytics (pre-field work)
►On-site interviews and substantive
testing
►M&A Due Diligence
►3rd Party Due Diligence
►3rd Party Risk profiling
►Conduct background checks
►Investigations
►Fraud response
planning
►Forensic data
analytics
►Discovery and
document
review
Code of Ethics
Fraud and Corruption Prevention
Policies
Communication and Training
Risk Assessment
Controls Monitoring
and Analytics
Incident Response
Plan
Reactive
Proactive
Setting the Proper Tone
Management Ownership and Involvement
Focus on analytics
Components of an Effective Anti-Fraud/
ABaC Compliance Program
®2013 Association of Certified Fraud Examiners, Inc.
12 of 31
Conducting a Fraud Risk Assessment
Code of Ethics
Fraud and Corruption Prevention
Policies
Communication and Training
Risk Assessment
Controls Monitoring
and Analytics
Incident Response
Plan
Reactive
Proactive
Setting the Proper Tone
Management Ownership and Involvement
®2013 Association of Certified Fraud Examiners, Inc.
13 of 31
Using a Heat Map to Prioritize
Compliance or Fraud Risks
®2013 Association of Certified Fraud Examiners, Inc.
14 of 31
Risk Assessment: Using the Result Improve
• High risk exposures with low levels of control
form the priorities for improvement
opportunities.
Verify
• High risk exposures with strong controls and
management efforts form the focus for audit
to provide assurance that controls are
adequate and efficient.
Monitor
• Low risk exposures accompanied by a lower
level of control are often considered emerging
and must remain a focus of ongoing
monitoring efforts
Optimize
• Low risk exposures with a moderate level of
control may be consciously accepted or may
be a focus to optimize the processes and
controls for greater efficiency.
Verify Improve
Monitor Optimize
®2013 Association of Certified Fraud Examiners, Inc.
16 of 31
Code of Ethics
Fraud and Corruption Prevention
Policies
Communication and Training
Risk Assessment
Controls Monitoring
and Analytics
Incident Response
Plan
Reactive
Proactive
Setting the Proper Tone
Management Ownership and Involvement
Now Let’s Talk About Analytics!
®2013 Association of Certified Fraud Examiners, Inc.
17 of 31
Gartner’s Business
Intelligence Maturity Model
Only about 10% of businesses use predictive
analytics right now and only 3% use prescriptive
Source: Gartner Research
®2013 Association of Certified Fraud Examiners, Inc.
18 of 31
Emerging Trends: Information and Analytics
Descriptive Analytics
What is happening?
Diagnostic Analytics
Why did it happen?
Predictive Analytics
What is likely to happen?
Prescriptive Analytics
What should I do about it?
Structured Hybrid Unstructured
/ Content
Source: Gartner Research
®2013 Association of Certified Fraud Examiners, Inc.
19 of 31
How Is Fraud Detected?
Source: ACFE 2010 Report to the Nations On Occupational Fraud
50% by tip or accident! Heavy use of “descriptive” analytics, if at all.
2012 ACFE Report to the Nations on Occupational Fraud
®2013 Association of Certified Fraud Examiners, Inc.
20 of 31
False Positive Rate High Low
Str
uc
ture
d
Da
ta
Detection Rate Low High
Un
str
uc
ture
d
Da
ta
“Traditional” rules-Based Queries & Analytics
Matching, Grouping, Ordering,
Joining, Filtering
Statistical-Based Analysis
Anomaly Detection, Clustering
Risk Ranking
Traditional Keyword Searching
Keyword Search
Data Visualization & Text Mining
Data visualization, Drill-down
into data, Text Mining
Forensic Analytics Maturity Model Beyond traditional “rules-based queries”—consider all 4 quadrants
®2013 Association of Certified Fraud Examiners, Inc.
21 of 31
Focus on the Payment Text Descriptions What if you saw these terms used as justification for payments to third parties?
<blank description>
Donation
Pay on behalf of
Special payment
Volume contract incentive
One-time payment
Special commission
Incentive payment
Team-building expense
Friend fee
Nobody calls it “bribe expense”
Commission to the customer
Consulting fee
Government fee
Processing fee
Goodwill payment
®2013 Association of Certified Fraud Examiners, Inc.
23 of 31
Beyond Rules-Based Tests
Beyond traditional matching, filtering, and sorting algorithms
Integrate statistical, visual, and text mining
techniques to identify patterns of high risk or
rogue employee activities
®2013 Association of Certified Fraud Examiners, Inc.
24 of 31
Technical Baseline
The right tools for the right
job
Working with IT
Data-mapping exercise
®2013 Association of Certified Fraud Examiners, Inc.
25 of 31
The Right Tools for the Right Job Partial list of examples
False Positive Rate High Low
Str
uc
ture
d
Da
ta
Detection Rate Low High
Un
str
uc
ture
d
Da
ta
Rules Based Queries & Analytics
Excel, Access, ACL,
SQL Server
Statistical-Based Analysis
SPSS, SAS, R, SAP Hana
Traditional Keyword Searching
dtSearch
Data Visualization & Text Mining
Tableau, i2, SPSS, SAS
®2013 Association of Certified Fraud Examiners, Inc.
26 of 31
Working With IT
Design your analytics based on fraud risks
Then determine your required data sources Structured and unstructured data
Prepare a data-request memo Specify table names if possible or field names if unknown
Specify desired data output (e.g., flat file, CSV, etc.)
Specify time frame
Be prepared to walk IT through your data
request
®2013 Association of Certified Fraud Examiners, Inc.
27 of 31
Common Data Sources:
Asset Misappropriation Schemes
Source Data
Vendor master Lists all approved vendors
Employee master Lists all employees
Accounts payable ledger Tracks when and to whom payments are due
Cash disbursements journal Tracks all cash disbursements
Purchases journal Tracks requests for purchases
Depending on the case, selected general ledger
accounts may also be selected.
®2013 Association of Certified Fraud Examiners, Inc.
28 of 31
Common Data Sources:
Bribery and Corruption Schemes
Source Data
Vendor master Lists all approved vendors
Accounts payable ledger Tracks when and to whom payments are due
Cash disbursements journal Tracks all cash disbursements
Purchases journal Tracks requests for purchases
Selected GL accounts
• Charity/donations
• Agent payments
• Marketing expenses
Identifies accounts where a bribe payment
could be hidden
Travel & entertainment Item detail of T&E submissions
®2013 Association of Certified Fraud Examiners, Inc.
29 of 31
DOJ/SEC Guidance on Where
Bribery Risks Exist
DOJ/SEC FCPA
Resource Guide
– Nov. 2012
®2013 Association of Certified Fraud Examiners, Inc.
30 of 31
Common Data Sources:
Financial Misstatements
Source Data
Sales journal Sales by product, date, customer
Accounts receivable Tracks amounts due to company by customer, over
time
Customer master Lists all customers
Various sub-ledgers May include inventory, capital expenses, outstanding
loans, etc.