SlideShare a Scribd company logo
FRAUD
ANALYTICS
M S M 5 3 3 B U S I N E S S A N A L Y T I
C S & D A T A G O V E R N A N C E
Simran Mondal 1918107
Christ University Bangalore
1. INTRODUCTION
2. IMPORTANCE
3. FRAUD DETECTION & PREVENTION
4. STEPS
5. METHODS
6. TOOLS
7. CRITICISM
8. CASE STUDY
9. REFERENCES
F R A U D A N A L Y T I C S
PRESENTATION
SUMMARY
Fraud Analytics is the process of integration of
analytical tools and techniques with human
interaction
In other words, it involves gathering and storing
relevant data and mining it for patterns,
discrepancies, and anomalies. The findings are
then translated into insights that can allow a
company to manage potential threats before they
occur as well as develop a proactive fraud and
bribery detection environment.
What is
Fraud
Analytics?
01
F R A U D A N A L Y T I C S
“Organizations lose an estimated 5 percent of their annual revenue to fraud, according to a
survey of fraud experts conducted by the Association of Certified Fraud Examiners.”
Why do we need Fraud Analytics?
02
Identify Hidden Patterns: Taking advantages of the digital fingerprints and tracing back to the
fraud is one of the advantages of using a Fraud Analytics tool
1
2
3
4
5
Data Integration: Fraud analytics plays an important role in integrating data. It combines data
from various sources and public records that can be integrated into a model.
Enhance existing efforts: Fraud Analytics is one step ahead of the traditional data storage
and retrieval mechanism by integrating data from various sources and files.
Harnessing unstructured data: Fraud analytics helps in deriving the best value from unstructured data.
Unstructured data is the place where more fraudulent activities take place. This is where text analytics
plays an important role in reviewing the unstructured data and preventing fraud from taking place.
Improve the performance: Fraud Analytics is a highly flexible and adaptable process which
can be customized to the needs of your organisation
Fraud Detection & Fraud Prevention
Fraud Detection Fraud Prevention
It is the identification of actual or expected fraud to
take place in an organization. Fraud detection in
today’s world involves a comprehensive approach to
match data points with activities to find what is
abnormal
● Fraud detection occurs during the fraud attempt
● The goal of fraud detection is to mitigate fraud
● Sophisticated fraud detection solutions also
reduce false positives which improves the user
experience and increases the productivity of fraud
teams
It is the implementation of a strategy to detect
fraudulent transactions or banking actions and
prevent these actions from causing financial and
reputational damage to the customer and financial
institution
● Fraud prevention occurs before the fraud
attempt
● The goal of fraud prevention is to reduce the
risk of future fraud
03
Steps to create your Fraud Programme
Create a profile that
includes all the areas
where fraud is expected
to occur and the
possible types of fraud
in those areas.
Measure the risk of fraud
and the overall exposure
to the organization.
Prioritize the risks based
on fraud.
Follow Fraud testing
method to find for
indicators of fraud
in particular areas of
organization
Establish risk
assessment and
decide where to pay
closer attention
Monitor the activity and
communicate it throughout the
organization so that employees
in the organization are aware
about the happening in the
organization
If there is any fraud found
out, inform the
management immediately
to solve out the issue and
to find out why it happened
Fix any broken
controls
Expand the
scope of the
program and
repeat the
process
04
Methods of Fraud Analytics
CONTINUOUS
ANALYSIS
05
Ad-Hoc is nothing
but finding out
fraud by means
of a hypothesis. It
allows you to
explore.
Transactions are
scanned in order
to find any
discrepancies or
fraud
It involves
hypothesis testing
and fraud
investigation
Sampling is the
method of testing
a sample for fraud
rather than the
whole population.
More effective
with larger
population Its main
disadvantage is
that it may not be
able to fully control
the fraud detection
as it takes only
few population
into consideration.
It means creating
and setting up
scripts to run
against big
volume of data to
identify the
frauds as they
occur over a
period of time.
It involves
periodic
notifications and
real time
detection of
fraud.
It helps to find out
frauds that are
not normal.
Calculate
Statistical
parameters to
find out values that
exceed averages of
standard deviation.
Look at high and
low values and find
out the
anomalies(indicators
of fraud) there.
Benford’s
distribution is non-
uniform with
smaller digits more
likely than the
larger digits.
Using Benford’s
law you can test
certain points and
numbers and
identify those
which appear
frequently than
they are supposed
to and therefore
they are the
suspect.
SAMPLING
2. AD-
HOC
3.REPETITIVE/
CONTINUOUS
ANALYTICS
4.
ANALYTICAL
TECHNIQUES
5.
BENFORD’S
LAW
Effective tools to minimize fraud based activities
Data analytics & similar technologies are used to help organizations to detect & prevent fraud based
activities Fraud analytics is an umbrella term covering a lot of technologies
1. Business Intelligence:
In the fraud management space, BI can
be thought of as a descriptive
performance reporter. It summarizes
available data to provide business
dashboards and insights to business
leaders and fraud managers so they
can make more informed decisions.
A. Management Information: MI
relates to creating executive
dashboards, data visualisation, data
storytelling and any other reporting
methods.
B. Data Warehousing: A data
warehouse is a large collection of
business data used to help an
organization make decisions.
06
2. Data Science:
Data science relates to a set of more sophisticated technologies for performing predictive and
prescriptive analytics Predictive analytics is focused on making predictions about the future of unknown events
(or, in the case of fraud, current events outcomes). Prescriptive analytics relates to choosing the optimal
course of action based on the outcome of those predictions.
A. Artificial Intelligence: AI relates to the computer implementation of human thought processes in a
computerized and efficient fashion.
1. Machine Learning: Machine learning is a subset of AI that relates to the science of algorithms. Machine
learning is a set of numerous algorithmic techniques can be used to extract complex relationships in data
which a human could not find.
2. Deep Learning: Deep learning is a class of machine learning algorithms focused specifically on building
“deep” (multi- layered) neural networks, a form of AI widely used in fraud detection.
Fraud analytics can be defined as a multidisciplinary field that combines numerous
quantitative sciences in order to better understand fraud.
07
08
How Data Analytics Can Assist in Fraud Detection
It can handle
massive amount
of data
It can help assess
and improve internal
controls
It reduces sampling
errors.
It helps to revise or
reinforce policies
It can be used
reactively or
proactively
It can track trends and possible
problems substantially faster
than people could, without help
Data analytics in Fraud detection refers to the use of analytics software to identify trends, patterns, spotting
anomalies, and exceptions in data.
● Applying fraud investigation skills to the data analysis results can help identify potential instance for
fraud.
● Data analysis techniques alone are unlikely to detect fraud; human judgment is needed to decipher
results.
Challenges Faced by Fraud Analytics
1. Changing Fraud Patterns overtime: fraudsters are always looking to find new and innovative
ways to get around the systems to commit fraud. Hence it is important to update with the
evolved patterns to detect. This results in a decrease in the model’s performance and
efficiency.
2. Class Imbalance: An imbalance in the classification of fraud detection models (that usually
classify transactions as either fraudulent or non-fraudulent) which makes it harder to build
them. The fallout of this challenge is a poor user experience for genuine customers, since
catching the fraudsters usually involves declining some legitimate transactions.
3. Model Interpretations: The models only give a score whether a transaction is fraudulent or
not, without giving any explanation.
4. Quality of the Data: The results from analytics tests can only be as good as the data we feed
in as input.
09
Case Study: How Fraud Analytics was instrumental in
curbing airline loyalty fraud
Airline travel miles are a coveted loyalty benefit, a gateway for customers to visit places new and old. To an unscrupulous
ticket agent, travel rewards present a good-as-gold opportunity to fraudulently issue miles and then redeem them to book
flights for personal and friends’ use. One major airline recently introduced data analytics into its fraud risk management
processes to identify anomalies, patterns, and trends signalling the potential for fraudulent activity. The analysis honed in
on a variety of data elements, such as number of air miles awarded to customers and agents, flights booked using air
miles, dates of awards, dates of travel, and more. Analysis of these data elements can produce key indicators of potential
fraud, such as:
● Anomaly detection: Were excessive air miles awarded by a single agent or to a single rewards account?
● Predictive classification: Are fraudulently awarded air miles being used to book particular flights?
● Clustering: Are there commonalities in the miles accruing to a rewards account, i.e., the same number of miles every
Wednesday, or the same approving manager sanctioning the awards?
● By leveraging a variety of analytics models: and by testing hypotheses through analysis of combined datasets,
the airline detected fraudulent activity earlier.
Further, by carefully considering the requirements to operationalize fraud risk analytics, and inventorying current tools and
technologies, the company determined that much of what it needed to perform the analytics was already in place, thereby
substantially reducing upfront technology investments.
10
References
1. https://www.educba.com/fraud-detection-analytics/
2. https://www2.deloitte.com/us/en/pages/advisory/articles/five-insights-into-fraud-risk-analytics.html
3. https://searchsecurity.techtarget.com/definition/fraud-
detection#:~:text=Fraud%20detection%20is%20a%20set,or%20using%20stolen%20credit%20cards.
4. https://www.sas.com/en_in/insights/articles/risk-fraud/fraud-detection-machine-learning.html
5. https://www.crisil.com/en/home/our-businesses/grna/risk-and-analytics/financial-crime-analytics-capabilities/fraud-
detection-and-analytics.html
6. https://www.rd-alliance.org/group/big-data-ig-data-development-ig/wiki/big-data-definition-importance-examples-
tools#:~:text=Big%20data%20is%20a%20term,amount%20of%20data%20that's%20important.&text=Big%20data%20ca
n%20be%20analyzed,decisions%20and%20strategic%20business%20moves.
7. https://www2.deloitte.com/content/dam/Deloitte/tr/Documents/deloitte-analytics/tr-fraud-analytics.pdf
8. https://www.fico.com/blogs/search?keywords%5B%5D=fraud
9. https://www.fico.com/blogs/controlling-obvious-and-hidden-fraud-threats-cristiano-ronaldo-syndrome
10.https://www.crisil.com/en/home/our-businesses/grna/risk-and-analytics/financial-crime-analytics-capabilities/fraud-
detection-and-analytics.html

More Related Content

What's hot

Fraud prevention detection control fuh 12
Fraud prevention detection control fuh  12Fraud prevention detection control fuh  12
Fraud prevention detection control fuh 12Fuh George Cheo
 
Social networking and identity theft
Social networking and identity theft Social networking and identity theft
Social networking and identity theft carlgiardina
 
ACFE Presentation on Analytics for Fraud Detection and Mitigation
ACFE Presentation on Analytics for Fraud Detection and MitigationACFE Presentation on Analytics for Fraud Detection and Mitigation
ACFE Presentation on Analytics for Fraud Detection and MitigationScott Mongeau
 
Online Payment Fraud Detection with Azure Machine Learning
Online Payment Fraud Detection with Azure Machine LearningOnline Payment Fraud Detection with Azure Machine Learning
Online Payment Fraud Detection with Azure Machine LearningStefano Tempesta
 
Causes, Effects and Management of Fraud: A Study with reference to Indian Ban...
Causes, Effects and Management of Fraud: A Study with reference to Indian Ban...Causes, Effects and Management of Fraud: A Study with reference to Indian Ban...
Causes, Effects and Management of Fraud: A Study with reference to Indian Ban...central university of rajasthan
 
How to Spot and Combat a Phishing Attack - Cyber Security Webinar | ControlScan
How to Spot and Combat a Phishing Attack - Cyber Security Webinar | ControlScanHow to Spot and Combat a Phishing Attack - Cyber Security Webinar | ControlScan
How to Spot and Combat a Phishing Attack - Cyber Security Webinar | ControlScanControlScan, Inc.
 
Fraud Presentation
Fraud PresentationFraud Presentation
Fraud Presentationmbachnak
 
Bank Fraud & Data Forensics
Bank Fraud & Data ForensicsBank Fraud & Data Forensics
Bank Fraud & Data Forensicswhbrown5
 
PHISHING PROJECT REPORT
PHISHING PROJECT REPORTPHISHING PROJECT REPORT
PHISHING PROJECT REPORTvineetkathan
 
Introduction To Analytics
Introduction To AnalyticsIntroduction To Analytics
Introduction To AnalyticsAlex Meadows
 

What's hot (20)

Fraud prevention detection control fuh 12
Fraud prevention detection control fuh  12Fraud prevention detection control fuh  12
Fraud prevention detection control fuh 12
 
Credit card frauds
Credit card fraudsCredit card frauds
Credit card frauds
 
Social networking and identity theft
Social networking and identity theft Social networking and identity theft
Social networking and identity theft
 
Cyber fraud in banks
Cyber fraud in banksCyber fraud in banks
Cyber fraud in banks
 
ACFE Presentation on Analytics for Fraud Detection and Mitigation
ACFE Presentation on Analytics for Fraud Detection and MitigationACFE Presentation on Analytics for Fraud Detection and Mitigation
ACFE Presentation on Analytics for Fraud Detection and Mitigation
 
Online Payment Fraud Detection with Azure Machine Learning
Online Payment Fraud Detection with Azure Machine LearningOnline Payment Fraud Detection with Azure Machine Learning
Online Payment Fraud Detection with Azure Machine Learning
 
Data breach
Data breachData breach
Data breach
 
Identity theft
Identity theftIdentity theft
Identity theft
 
Causes, Effects and Management of Fraud: A Study with reference to Indian Ban...
Causes, Effects and Management of Fraud: A Study with reference to Indian Ban...Causes, Effects and Management of Fraud: A Study with reference to Indian Ban...
Causes, Effects and Management of Fraud: A Study with reference to Indian Ban...
 
How to Spot and Combat a Phishing Attack - Cyber Security Webinar | ControlScan
How to Spot and Combat a Phishing Attack - Cyber Security Webinar | ControlScanHow to Spot and Combat a Phishing Attack - Cyber Security Webinar | ControlScan
How to Spot and Combat a Phishing Attack - Cyber Security Webinar | ControlScan
 
Trends in AML Compliance and Technology
Trends in AML Compliance and TechnologyTrends in AML Compliance and Technology
Trends in AML Compliance and Technology
 
Fraud Presentation
Fraud PresentationFraud Presentation
Fraud Presentation
 
Types of Fraud.pptx
Types of Fraud.pptxTypes of Fraud.pptx
Types of Fraud.pptx
 
What is Phishing and How can you Avoid it?
What is Phishing and How can you Avoid it?What is Phishing and How can you Avoid it?
What is Phishing and How can you Avoid it?
 
Bank Fraud & Data Forensics
Bank Fraud & Data ForensicsBank Fraud & Data Forensics
Bank Fraud & Data Forensics
 
Mobile Payment fraud & risk assessment
Mobile Payment fraud & risk assessmentMobile Payment fraud & risk assessment
Mobile Payment fraud & risk assessment
 
PHISHING PROJECT REPORT
PHISHING PROJECT REPORTPHISHING PROJECT REPORT
PHISHING PROJECT REPORT
 
Online Scams and Frauds
Online Scams and FraudsOnline Scams and Frauds
Online Scams and Frauds
 
Introduction To Analytics
Introduction To AnalyticsIntroduction To Analytics
Introduction To Analytics
 
Bank frauds
Bank fraudsBank frauds
Bank frauds
 

Similar to Fraud analytics

Big Data Analytics Fraud Detection and Risk Management in Fintech.pdf
Big Data Analytics Fraud Detection and Risk Management in Fintech.pdfBig Data Analytics Fraud Detection and Risk Management in Fintech.pdf
Big Data Analytics Fraud Detection and Risk Management in Fintech.pdfSmartinfologiks
 
RSB72-PPT.pptx
RSB72-PPT.pptxRSB72-PPT.pptx
RSB72-PPT.pptxAryanGour1
 
IRJET- A Comparative Study to Detect Fraud Financial Statement using Data Min...
IRJET- A Comparative Study to Detect Fraud Financial Statement using Data Min...IRJET- A Comparative Study to Detect Fraud Financial Statement using Data Min...
IRJET- A Comparative Study to Detect Fraud Financial Statement using Data Min...IRJET Journal
 
Claims Fraud Network Analysis
Claims Fraud Network AnalysisClaims Fraud Network Analysis
Claims Fraud Network AnalysisCogitate.us
 
Board matters quarterly – volume 3
Board matters quarterly – volume 3Board matters quarterly – volume 3
Board matters quarterly – volume 3elithomas202
 
Enterprise Fraud Management: How Banks Need to Adapt
Enterprise Fraud Management: How Banks Need to AdaptEnterprise Fraud Management: How Banks Need to Adapt
Enterprise Fraud Management: How Banks Need to AdaptCapgemini
 
Emerging technologies enabling in fraud detection
Emerging technologies enabling in fraud detectionEmerging technologies enabling in fraud detection
Emerging technologies enabling in fraud detectionUmasree Raghunath
 
160987-time-template-4x3.pptx
160987-time-template-4x3.pptx160987-time-template-4x3.pptx
160987-time-template-4x3.pptxAryanGour1
 
Using Data Analytics to Conduct a Forensic Audit
Using Data Analytics to Conduct a Forensic AuditUsing Data Analytics to Conduct a Forensic Audit
Using Data Analytics to Conduct a Forensic AuditFraudBusters
 
Ai and machine learning help detect, predict and prevent fraud - IBM Watson ...
Ai and machine learning help detect, predict and prevent fraud -  IBM Watson ...Ai and machine learning help detect, predict and prevent fraud -  IBM Watson ...
Ai and machine learning help detect, predict and prevent fraud - IBM Watson ...Institute of Contemporary Sciences
 
FRAUD DETECTION IN CREDIT CARD TRANSACTIONS
FRAUD DETECTION IN CREDIT CARD TRANSACTIONSFRAUD DETECTION IN CREDIT CARD TRANSACTIONS
FRAUD DETECTION IN CREDIT CARD TRANSACTIONSIRJET Journal
 
Anti-Fraud 1Anti-Fraud PreventionName.docx
Anti-Fraud     1Anti-Fraud PreventionName.docxAnti-Fraud     1Anti-Fraud PreventionName.docx
Anti-Fraud 1Anti-Fraud PreventionName.docxrossskuddershamus
 
Managing The Business Risk Of Fraud
Managing The Business Risk Of FraudManaging The Business Risk Of Fraud
Managing The Business Risk Of FraudEZ-R Stats, LLC
 
5 Applications of Data Science in FinTech: The Tech Behind the Booming FinTec...
5 Applications of Data Science in FinTech: The Tech Behind the Booming FinTec...5 Applications of Data Science in FinTech: The Tech Behind the Booming FinTec...
5 Applications of Data Science in FinTech: The Tech Behind the Booming FinTec...Kavika Roy
 
Utilizing Machine Learning In Banking To Prevent Fraud.pdf
Utilizing Machine Learning In Banking To Prevent Fraud.pdfUtilizing Machine Learning In Banking To Prevent Fraud.pdf
Utilizing Machine Learning In Banking To Prevent Fraud.pdfMindfire LLC
 
Fortify Your Enterprise with IBM Smarter Counter-Fraud Solutions
Fortify Your Enterprise with IBM Smarter Counter-Fraud SolutionsFortify Your Enterprise with IBM Smarter Counter-Fraud Solutions
Fortify Your Enterprise with IBM Smarter Counter-Fraud SolutionsPerficient, Inc.
 
Insight2014 mitigate risk_fraud_6863
Insight2014 mitigate risk_fraud_6863Insight2014 mitigate risk_fraud_6863
Insight2014 mitigate risk_fraud_6863IBMgbsNA
 
Cybersource 2013 Online Fraud Report
Cybersource 2013 Online Fraud ReportCybersource 2013 Online Fraud Report
Cybersource 2013 Online Fraud ReportJoshua Enders
 
Transactional Fraud Detection A Modular Approach
Transactional Fraud Detection   A Modular ApproachTransactional Fraud Detection   A Modular Approach
Transactional Fraud Detection A Modular ApproachNoreen Buckley
 

Similar to Fraud analytics (20)

Big Data Analytics Fraud Detection and Risk Management in Fintech.pdf
Big Data Analytics Fraud Detection and Risk Management in Fintech.pdfBig Data Analytics Fraud Detection and Risk Management in Fintech.pdf
Big Data Analytics Fraud Detection and Risk Management in Fintech.pdf
 
RSB72-PPT.pptx
RSB72-PPT.pptxRSB72-PPT.pptx
RSB72-PPT.pptx
 
IRJET- A Comparative Study to Detect Fraud Financial Statement using Data Min...
IRJET- A Comparative Study to Detect Fraud Financial Statement using Data Min...IRJET- A Comparative Study to Detect Fraud Financial Statement using Data Min...
IRJET- A Comparative Study to Detect Fraud Financial Statement using Data Min...
 
Claims Fraud Network Analysis
Claims Fraud Network AnalysisClaims Fraud Network Analysis
Claims Fraud Network Analysis
 
Board matters quarterly – volume 3
Board matters quarterly – volume 3Board matters quarterly – volume 3
Board matters quarterly – volume 3
 
Enterprise Fraud Management: How Banks Need to Adapt
Enterprise Fraud Management: How Banks Need to AdaptEnterprise Fraud Management: How Banks Need to Adapt
Enterprise Fraud Management: How Banks Need to Adapt
 
Emerging technologies enabling in fraud detection
Emerging technologies enabling in fraud detectionEmerging technologies enabling in fraud detection
Emerging technologies enabling in fraud detection
 
160987-time-template-4x3.pptx
160987-time-template-4x3.pptx160987-time-template-4x3.pptx
160987-time-template-4x3.pptx
 
Using Data Analytics to Conduct a Forensic Audit
Using Data Analytics to Conduct a Forensic AuditUsing Data Analytics to Conduct a Forensic Audit
Using Data Analytics to Conduct a Forensic Audit
 
Ai and machine learning help detect, predict and prevent fraud - IBM Watson ...
Ai and machine learning help detect, predict and prevent fraud -  IBM Watson ...Ai and machine learning help detect, predict and prevent fraud -  IBM Watson ...
Ai and machine learning help detect, predict and prevent fraud - IBM Watson ...
 
FRAUD DETECTION IN CREDIT CARD TRANSACTIONS
FRAUD DETECTION IN CREDIT CARD TRANSACTIONSFRAUD DETECTION IN CREDIT CARD TRANSACTIONS
FRAUD DETECTION IN CREDIT CARD TRANSACTIONS
 
Credit Card Fraud Detection_ Mansi_Choudhary.pptx
Credit Card Fraud Detection_ Mansi_Choudhary.pptxCredit Card Fraud Detection_ Mansi_Choudhary.pptx
Credit Card Fraud Detection_ Mansi_Choudhary.pptx
 
Anti-Fraud 1Anti-Fraud PreventionName.docx
Anti-Fraud     1Anti-Fraud PreventionName.docxAnti-Fraud     1Anti-Fraud PreventionName.docx
Anti-Fraud 1Anti-Fraud PreventionName.docx
 
Managing The Business Risk Of Fraud
Managing The Business Risk Of FraudManaging The Business Risk Of Fraud
Managing The Business Risk Of Fraud
 
5 Applications of Data Science in FinTech: The Tech Behind the Booming FinTec...
5 Applications of Data Science in FinTech: The Tech Behind the Booming FinTec...5 Applications of Data Science in FinTech: The Tech Behind the Booming FinTec...
5 Applications of Data Science in FinTech: The Tech Behind the Booming FinTec...
 
Utilizing Machine Learning In Banking To Prevent Fraud.pdf
Utilizing Machine Learning In Banking To Prevent Fraud.pdfUtilizing Machine Learning In Banking To Prevent Fraud.pdf
Utilizing Machine Learning In Banking To Prevent Fraud.pdf
 
Fortify Your Enterprise with IBM Smarter Counter-Fraud Solutions
Fortify Your Enterprise with IBM Smarter Counter-Fraud SolutionsFortify Your Enterprise with IBM Smarter Counter-Fraud Solutions
Fortify Your Enterprise with IBM Smarter Counter-Fraud Solutions
 
Insight2014 mitigate risk_fraud_6863
Insight2014 mitigate risk_fraud_6863Insight2014 mitigate risk_fraud_6863
Insight2014 mitigate risk_fraud_6863
 
Cybersource 2013 Online Fraud Report
Cybersource 2013 Online Fraud ReportCybersource 2013 Online Fraud Report
Cybersource 2013 Online Fraud Report
 
Transactional Fraud Detection A Modular Approach
Transactional Fraud Detection   A Modular ApproachTransactional Fraud Detection   A Modular Approach
Transactional Fraud Detection A Modular Approach
 

More from Simran Mondal

Burger king -Marketing startegies
Burger king -Marketing startegiesBurger king -Marketing startegies
Burger king -Marketing startegiesSimran Mondal
 
HUMANISTIC APPROACH TO LIFESPAN DEVELOPMENT
HUMANISTIC APPROACH TO LIFESPAN DEVELOPMENTHUMANISTIC APPROACH TO LIFESPAN DEVELOPMENT
HUMANISTIC APPROACH TO LIFESPAN DEVELOPMENTSimran Mondal
 
Biopsychosocial approach to my menstrual cycle
 Biopsychosocial approach to my menstrual cycle Biopsychosocial approach to my menstrual cycle
Biopsychosocial approach to my menstrual cycleSimran Mondal
 
McDonalds leadership lessons
McDonalds leadership lessonsMcDonalds leadership lessons
McDonalds leadership lessonsSimran Mondal
 
Marketing management Burger king
Marketing management Burger king Marketing management Burger king
Marketing management Burger king Simran Mondal
 
Ford motor company leadership lessons
Ford motor company   leadership lessonsFord motor company   leadership lessons
Ford motor company leadership lessonsSimran Mondal
 
Product marketing plan Flying cars
Product marketing plan   Flying carsProduct marketing plan   Flying cars
Product marketing plan Flying carsSimran Mondal
 

More from Simran Mondal (10)

Burger king -Marketing startegies
Burger king -Marketing startegiesBurger king -Marketing startegies
Burger king -Marketing startegies
 
HUMANISTIC APPROACH TO LIFESPAN DEVELOPMENT
HUMANISTIC APPROACH TO LIFESPAN DEVELOPMENTHUMANISTIC APPROACH TO LIFESPAN DEVELOPMENT
HUMANISTIC APPROACH TO LIFESPAN DEVELOPMENT
 
Ethics at workplace
Ethics at workplaceEthics at workplace
Ethics at workplace
 
Biopsychosocial approach to my menstrual cycle
 Biopsychosocial approach to my menstrual cycle Biopsychosocial approach to my menstrual cycle
Biopsychosocial approach to my menstrual cycle
 
Cystic fibrosis
Cystic fibrosisCystic fibrosis
Cystic fibrosis
 
Elss
ElssElss
Elss
 
McDonalds leadership lessons
McDonalds leadership lessonsMcDonalds leadership lessons
McDonalds leadership lessons
 
Marketing management Burger king
Marketing management Burger king Marketing management Burger king
Marketing management Burger king
 
Ford motor company leadership lessons
Ford motor company   leadership lessonsFord motor company   leadership lessons
Ford motor company leadership lessons
 
Product marketing plan Flying cars
Product marketing plan   Flying carsProduct marketing plan   Flying cars
Product marketing plan Flying cars
 

Recently uploaded

Predicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Predicting Product Ad Campaign Performance: A Data Analysis Project PresentationPredicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Predicting Product Ad Campaign Performance: A Data Analysis Project PresentationBoston Institute of Analytics
 
一比一原版(YU毕业证)约克大学毕业证成绩单
一比一原版(YU毕业证)约克大学毕业证成绩单一比一原版(YU毕业证)约克大学毕业证成绩单
一比一原版(YU毕业证)约克大学毕业证成绩单enxupq
 
tapal brand analysis PPT slide for comptetive data
tapal brand analysis PPT slide for comptetive datatapal brand analysis PPT slide for comptetive data
tapal brand analysis PPT slide for comptetive datatheahmadsaood
 
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单ewymefz
 
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...elinavihriala
 
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单ewymefz
 
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单ukgaet
 
Empowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptxEmpowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptxbenishzehra469
 
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单vcaxypu
 
一比一原版(QU毕业证)皇后大学毕业证成绩单
一比一原版(QU毕业证)皇后大学毕业证成绩单一比一原版(QU毕业证)皇后大学毕业证成绩单
一比一原版(QU毕业证)皇后大学毕业证成绩单enxupq
 
Introduction-to-Cybersecurit57hhfcbbcxxx
Introduction-to-Cybersecurit57hhfcbbcxxxIntroduction-to-Cybersecurit57hhfcbbcxxx
Introduction-to-Cybersecurit57hhfcbbcxxxzahraomer517
 
Jpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization SampleJpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization SampleJames Polillo
 
Uber Ride Supply Demand Gap Analysis Report
Uber Ride Supply Demand Gap Analysis ReportUber Ride Supply Demand Gap Analysis Report
Uber Ride Supply Demand Gap Analysis ReportSatyamNeelmani2
 
Business update Q1 2024 Lar España Real Estate SOCIMI
Business update Q1 2024 Lar España Real Estate SOCIMIBusiness update Q1 2024 Lar España Real Estate SOCIMI
Business update Q1 2024 Lar España Real Estate SOCIMIAlejandraGmez176757
 
standardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhstandardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhArpitMalhotra16
 
一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单ewymefz
 
Computer Presentation.pptx ecommerce advantage s
Computer Presentation.pptx ecommerce advantage sComputer Presentation.pptx ecommerce advantage s
Computer Presentation.pptx ecommerce advantage sMAQIB18
 
Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...
Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...
Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...Domenico Conte
 
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPsWebinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPsCEPTES Software Inc
 
一比一原版(UofM毕业证)明尼苏达大学毕业证成绩单
一比一原版(UofM毕业证)明尼苏达大学毕业证成绩单一比一原版(UofM毕业证)明尼苏达大学毕业证成绩单
一比一原版(UofM毕业证)明尼苏达大学毕业证成绩单ewymefz
 

Recently uploaded (20)

Predicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Predicting Product Ad Campaign Performance: A Data Analysis Project PresentationPredicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Predicting Product Ad Campaign Performance: A Data Analysis Project Presentation
 
一比一原版(YU毕业证)约克大学毕业证成绩单
一比一原版(YU毕业证)约克大学毕业证成绩单一比一原版(YU毕业证)约克大学毕业证成绩单
一比一原版(YU毕业证)约克大学毕业证成绩单
 
tapal brand analysis PPT slide for comptetive data
tapal brand analysis PPT slide for comptetive datatapal brand analysis PPT slide for comptetive data
tapal brand analysis PPT slide for comptetive data
 
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
 
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
 
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单
 
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
 
Empowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptxEmpowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptx
 
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
 
一比一原版(QU毕业证)皇后大学毕业证成绩单
一比一原版(QU毕业证)皇后大学毕业证成绩单一比一原版(QU毕业证)皇后大学毕业证成绩单
一比一原版(QU毕业证)皇后大学毕业证成绩单
 
Introduction-to-Cybersecurit57hhfcbbcxxx
Introduction-to-Cybersecurit57hhfcbbcxxxIntroduction-to-Cybersecurit57hhfcbbcxxx
Introduction-to-Cybersecurit57hhfcbbcxxx
 
Jpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization SampleJpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization Sample
 
Uber Ride Supply Demand Gap Analysis Report
Uber Ride Supply Demand Gap Analysis ReportUber Ride Supply Demand Gap Analysis Report
Uber Ride Supply Demand Gap Analysis Report
 
Business update Q1 2024 Lar España Real Estate SOCIMI
Business update Q1 2024 Lar España Real Estate SOCIMIBusiness update Q1 2024 Lar España Real Estate SOCIMI
Business update Q1 2024 Lar España Real Estate SOCIMI
 
standardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhstandardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghh
 
一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单
 
Computer Presentation.pptx ecommerce advantage s
Computer Presentation.pptx ecommerce advantage sComputer Presentation.pptx ecommerce advantage s
Computer Presentation.pptx ecommerce advantage s
 
Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...
Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...
Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...
 
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPsWebinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
 
一比一原版(UofM毕业证)明尼苏达大学毕业证成绩单
一比一原版(UofM毕业证)明尼苏达大学毕业证成绩单一比一原版(UofM毕业证)明尼苏达大学毕业证成绩单
一比一原版(UofM毕业证)明尼苏达大学毕业证成绩单
 

Fraud analytics

  • 1. FRAUD ANALYTICS M S M 5 3 3 B U S I N E S S A N A L Y T I C S & D A T A G O V E R N A N C E Simran Mondal 1918107 Christ University Bangalore
  • 2. 1. INTRODUCTION 2. IMPORTANCE 3. FRAUD DETECTION & PREVENTION 4. STEPS 5. METHODS 6. TOOLS 7. CRITICISM 8. CASE STUDY 9. REFERENCES F R A U D A N A L Y T I C S PRESENTATION SUMMARY
  • 3. Fraud Analytics is the process of integration of analytical tools and techniques with human interaction In other words, it involves gathering and storing relevant data and mining it for patterns, discrepancies, and anomalies. The findings are then translated into insights that can allow a company to manage potential threats before they occur as well as develop a proactive fraud and bribery detection environment. What is Fraud Analytics? 01 F R A U D A N A L Y T I C S “Organizations lose an estimated 5 percent of their annual revenue to fraud, according to a survey of fraud experts conducted by the Association of Certified Fraud Examiners.”
  • 4. Why do we need Fraud Analytics? 02 Identify Hidden Patterns: Taking advantages of the digital fingerprints and tracing back to the fraud is one of the advantages of using a Fraud Analytics tool 1 2 3 4 5 Data Integration: Fraud analytics plays an important role in integrating data. It combines data from various sources and public records that can be integrated into a model. Enhance existing efforts: Fraud Analytics is one step ahead of the traditional data storage and retrieval mechanism by integrating data from various sources and files. Harnessing unstructured data: Fraud analytics helps in deriving the best value from unstructured data. Unstructured data is the place where more fraudulent activities take place. This is where text analytics plays an important role in reviewing the unstructured data and preventing fraud from taking place. Improve the performance: Fraud Analytics is a highly flexible and adaptable process which can be customized to the needs of your organisation
  • 5. Fraud Detection & Fraud Prevention Fraud Detection Fraud Prevention It is the identification of actual or expected fraud to take place in an organization. Fraud detection in today’s world involves a comprehensive approach to match data points with activities to find what is abnormal ● Fraud detection occurs during the fraud attempt ● The goal of fraud detection is to mitigate fraud ● Sophisticated fraud detection solutions also reduce false positives which improves the user experience and increases the productivity of fraud teams It is the implementation of a strategy to detect fraudulent transactions or banking actions and prevent these actions from causing financial and reputational damage to the customer and financial institution ● Fraud prevention occurs before the fraud attempt ● The goal of fraud prevention is to reduce the risk of future fraud 03
  • 6. Steps to create your Fraud Programme Create a profile that includes all the areas where fraud is expected to occur and the possible types of fraud in those areas. Measure the risk of fraud and the overall exposure to the organization. Prioritize the risks based on fraud. Follow Fraud testing method to find for indicators of fraud in particular areas of organization Establish risk assessment and decide where to pay closer attention Monitor the activity and communicate it throughout the organization so that employees in the organization are aware about the happening in the organization If there is any fraud found out, inform the management immediately to solve out the issue and to find out why it happened Fix any broken controls Expand the scope of the program and repeat the process 04
  • 7. Methods of Fraud Analytics CONTINUOUS ANALYSIS 05 Ad-Hoc is nothing but finding out fraud by means of a hypothesis. It allows you to explore. Transactions are scanned in order to find any discrepancies or fraud It involves hypothesis testing and fraud investigation Sampling is the method of testing a sample for fraud rather than the whole population. More effective with larger population Its main disadvantage is that it may not be able to fully control the fraud detection as it takes only few population into consideration. It means creating and setting up scripts to run against big volume of data to identify the frauds as they occur over a period of time. It involves periodic notifications and real time detection of fraud. It helps to find out frauds that are not normal. Calculate Statistical parameters to find out values that exceed averages of standard deviation. Look at high and low values and find out the anomalies(indicators of fraud) there. Benford’s distribution is non- uniform with smaller digits more likely than the larger digits. Using Benford’s law you can test certain points and numbers and identify those which appear frequently than they are supposed to and therefore they are the suspect. SAMPLING 2. AD- HOC 3.REPETITIVE/ CONTINUOUS ANALYTICS 4. ANALYTICAL TECHNIQUES 5. BENFORD’S LAW
  • 8. Effective tools to minimize fraud based activities Data analytics & similar technologies are used to help organizations to detect & prevent fraud based activities Fraud analytics is an umbrella term covering a lot of technologies 1. Business Intelligence: In the fraud management space, BI can be thought of as a descriptive performance reporter. It summarizes available data to provide business dashboards and insights to business leaders and fraud managers so they can make more informed decisions. A. Management Information: MI relates to creating executive dashboards, data visualisation, data storytelling and any other reporting methods. B. Data Warehousing: A data warehouse is a large collection of business data used to help an organization make decisions. 06
  • 9. 2. Data Science: Data science relates to a set of more sophisticated technologies for performing predictive and prescriptive analytics Predictive analytics is focused on making predictions about the future of unknown events (or, in the case of fraud, current events outcomes). Prescriptive analytics relates to choosing the optimal course of action based on the outcome of those predictions. A. Artificial Intelligence: AI relates to the computer implementation of human thought processes in a computerized and efficient fashion. 1. Machine Learning: Machine learning is a subset of AI that relates to the science of algorithms. Machine learning is a set of numerous algorithmic techniques can be used to extract complex relationships in data which a human could not find. 2. Deep Learning: Deep learning is a class of machine learning algorithms focused specifically on building “deep” (multi- layered) neural networks, a form of AI widely used in fraud detection. Fraud analytics can be defined as a multidisciplinary field that combines numerous quantitative sciences in order to better understand fraud. 07
  • 10. 08 How Data Analytics Can Assist in Fraud Detection It can handle massive amount of data It can help assess and improve internal controls It reduces sampling errors. It helps to revise or reinforce policies It can be used reactively or proactively It can track trends and possible problems substantially faster than people could, without help Data analytics in Fraud detection refers to the use of analytics software to identify trends, patterns, spotting anomalies, and exceptions in data. ● Applying fraud investigation skills to the data analysis results can help identify potential instance for fraud. ● Data analysis techniques alone are unlikely to detect fraud; human judgment is needed to decipher results.
  • 11. Challenges Faced by Fraud Analytics 1. Changing Fraud Patterns overtime: fraudsters are always looking to find new and innovative ways to get around the systems to commit fraud. Hence it is important to update with the evolved patterns to detect. This results in a decrease in the model’s performance and efficiency. 2. Class Imbalance: An imbalance in the classification of fraud detection models (that usually classify transactions as either fraudulent or non-fraudulent) which makes it harder to build them. The fallout of this challenge is a poor user experience for genuine customers, since catching the fraudsters usually involves declining some legitimate transactions. 3. Model Interpretations: The models only give a score whether a transaction is fraudulent or not, without giving any explanation. 4. Quality of the Data: The results from analytics tests can only be as good as the data we feed in as input. 09
  • 12. Case Study: How Fraud Analytics was instrumental in curbing airline loyalty fraud Airline travel miles are a coveted loyalty benefit, a gateway for customers to visit places new and old. To an unscrupulous ticket agent, travel rewards present a good-as-gold opportunity to fraudulently issue miles and then redeem them to book flights for personal and friends’ use. One major airline recently introduced data analytics into its fraud risk management processes to identify anomalies, patterns, and trends signalling the potential for fraudulent activity. The analysis honed in on a variety of data elements, such as number of air miles awarded to customers and agents, flights booked using air miles, dates of awards, dates of travel, and more. Analysis of these data elements can produce key indicators of potential fraud, such as: ● Anomaly detection: Were excessive air miles awarded by a single agent or to a single rewards account? ● Predictive classification: Are fraudulently awarded air miles being used to book particular flights? ● Clustering: Are there commonalities in the miles accruing to a rewards account, i.e., the same number of miles every Wednesday, or the same approving manager sanctioning the awards? ● By leveraging a variety of analytics models: and by testing hypotheses through analysis of combined datasets, the airline detected fraudulent activity earlier. Further, by carefully considering the requirements to operationalize fraud risk analytics, and inventorying current tools and technologies, the company determined that much of what it needed to perform the analytics was already in place, thereby substantially reducing upfront technology investments. 10
  • 13. References 1. https://www.educba.com/fraud-detection-analytics/ 2. https://www2.deloitte.com/us/en/pages/advisory/articles/five-insights-into-fraud-risk-analytics.html 3. https://searchsecurity.techtarget.com/definition/fraud- detection#:~:text=Fraud%20detection%20is%20a%20set,or%20using%20stolen%20credit%20cards. 4. https://www.sas.com/en_in/insights/articles/risk-fraud/fraud-detection-machine-learning.html 5. https://www.crisil.com/en/home/our-businesses/grna/risk-and-analytics/financial-crime-analytics-capabilities/fraud- detection-and-analytics.html 6. https://www.rd-alliance.org/group/big-data-ig-data-development-ig/wiki/big-data-definition-importance-examples- tools#:~:text=Big%20data%20is%20a%20term,amount%20of%20data%20that's%20important.&text=Big%20data%20ca n%20be%20analyzed,decisions%20and%20strategic%20business%20moves. 7. https://www2.deloitte.com/content/dam/Deloitte/tr/Documents/deloitte-analytics/tr-fraud-analytics.pdf 8. https://www.fico.com/blogs/search?keywords%5B%5D=fraud 9. https://www.fico.com/blogs/controlling-obvious-and-hidden-fraud-threats-cristiano-ronaldo-syndrome 10.https://www.crisil.com/en/home/our-businesses/grna/risk-and-analytics/financial-crime-analytics-capabilities/fraud- detection-and-analytics.html