SlideShare a Scribd company logo
Big Data Analytical Driven Fraud Detection for Finance-
Banking and Insurance
 Customer data security is one of the biggest challenges that banks the world over face. A
few numbers show how significant this risk is:
 The Nilson Report estimates that in 2016, losses topped USD 24.71 billion. That represents a
12% increase over the previous year.
 According to a report from Javelin Strategy, there's a new identity theft victim every two
seconds, and many of the incidents involve credit cards.
 ACI Worldwide (an electronic payment systems company) estimates that 46% of Americans
have had their card information compromised at some point in the past 5 years.
 Approximately 65% of the time, credit card fraud results in a direct or indirect financial loss
for the victim.
 Among victims who reported direct financial losses, the average was $7,761 and the median
was $2,000 per victim. This is compared with those who suffered indirect losses with an
average of $261 and median of $10.
 23 frightening credit card statistics: Feb 1, 2017; Rebecca Lake; Available at:
https://www.creditdonkey.com/credit-card-fraud-statistics.html
 Fraud accounts for 5-10 percent of claims costs for U.S. and Canadian insurers.
Nearly one-third of insurers (32 percent) say fraud was as high as 20 percent of
claims costs;
 57 percent of insurers predict an increase in personal-property fraud by
policyholders. Around 58 percent say the same for personal auto insurance, and 69
percent expect a rise in workers-compensation scams;
 61 percent predict an increase in auto-insurance fraud by organized rings, and 55
percent predict an increase workers-compensation scamming;
 About 35 percent say fraud costs their companies 5-10 percent of claim volume.
More than 30 percent say fraud losses cost 10-20 percent of claim volume;
 Detecting fraud before claims are paid, and upgrading analytics, were mentioned
most often as the insurers’ main fraud-fighting priorities; and
 One-third of insurers don’t feel adequately protected against fraud. (FICO, August
2013)
 Insurance fraud statistics: Available at: http://www.insurancefraud.org/statistics.htm#2
 Insurance companies lose an estimated $30 billion per year in
insurance fraud costs that have to get passed on to bill-paying
consumers.
 The most common types of insurance fraud are:
 1) Stolen car
 2) car accident
 3) car damage
 4)health insurance billing fraud
 5) unnecessary medical procedures
 6) staged home fires
 7) storm fraud
 8) abandoned house fire
 9)faked death
 10) renter’s insurance
 Insurance fraud statistics: Available at: http://www.insurancefraud.org/statistics.htm#2
 Customer data security is one of the biggest challenges that banks the world over face but
Pakistani banks have now become even more vulnerable. A few quotes highlight why:
 “We not only face threats from hackers who skim ATMs or manipulate online accounts just for
swindling money, but also from organised hacking groups whose objectives are wider,”- the
head of a local bank.
 “Pakistan’s entire security establishment is walking a tight rope after entering into the CPEC
[China-Pakistan Economic Corridor]. Foreign powers are making every effort to embarrass the
country. We need to thoroughly investigate the real motives behind the recent skimming in the
light of previous bank data stealing incidents in which some Chinese nationals were involved,” a
well-placed source in the FIA
 Over the years, the use of ATMs has been growing rapidly in Pakistan. According to SBP
statistics, about 110m ATM transactions took place in just the nine months from July 2016 to
March 2017, with the total value of these transactions exceeding Rs960 billion. As banks
continue to encourage their clients to use ATMs and as people experience the benefits doing
so, these numbers are only poised to grow.
 In the current spree of ATM skimming, 296 customers of HBL have so far confirmed being
defrauded, an aggregate loss of PKR 10.2m, implied a press release issued by the State Bank
of Pakistan (SBP) on Dec 5. The number of bank accounts affected, though, is around 600,
according to newspaper reports.
 Apart from this, several such cases have been reported from Dolmen Mall, Karachi. Reports
also surfaced of a similar cyberattack in Islamabad. Banks including HBL responded by
blocking users’ ATM cards as a precaution against further loss.
 Rising Prevalence of ATM Fraud; Dec 11,2017; Dawn; Available at:
https://www.dawn.com/news/1375856
 Beware- Hackers are going after ATMs in Pakistan: Salman Siddiqui, Dec 3, 2017: The Express
Tribune: Available at: https://tribune.com.pk/story/1574702/2-beware-hackers-going-atms-
pakistan/
 The National Accountability Bureau (NAB) on Saturday arrested 23 accused officials
of State Life Insurance Corporation, including a regional manager, in a scam of over
Rs 100 million related to bogus policies. According to a NAB spokesman, the accused
caused the heavy loss through bogus insurance policies by opening 113 bank
accounts and withdrawing cash against over 430 cheques. He said the accused
officials facilitated fake policies to around 90 individuals who had never entered into
any policy with State Life Insurance. He said a local government councillor was also
among the arrested accused.
 Inflated health claims, stolen cars, money laundering and fraud through life insurance is
common but not properly analyzed and quantified. Central databases need to be made by
SECP regulator too.
 NAB arrests 23 officers in PKR 100 million insurance scam; April 17,2017; The News; Available
at:https://www.thenews.com.pk/print/199063-NAB-arrests-23-officers-in-Rs-100m-
insurance-scam
Culture
Level
Soft Facts
Organizational
Level
90% of the
problems
caused by
hacking
remain
undetected
and hidden
Hard Facts
Only 10% of the
problems caused by
hacking are brought
onto the surface
Top leadership Board of
Directors driven
initiative is key to
establishing
comprehensive Cyber
crime division in the
bank.
Availing latest technology
and analytics
Handling situations
correctly by the bank
and insurer
Big Data
Neural Networks
Machine Learning
Anomaly Detection
KPIs holistic; key
metrices
Clustering
Deep Learning
Fraud Analytics
Customer support
and awareness
Forensic IT
Handling situations
holistically
PR and Customer
perception handling
Preparing
contingency plans
for hacking
Holistically combating fraud
Deep Learning is based on neural networks
which mimic how our brain and neurons
work.
Big Data and Machine Learning Analytics
Big Data and Machine Learning Analytics
Being hacked is an inevitable fact of life and normal way
of doing business now. What matters now is how we
handle the crises when it occurs, and how much pre-
emptive preparations we take to minimize hacking
attempts. It’s important to remain at level with hackers on
technology and to utilize new technologies so that we
remain at the forefront of all cyber issues
Utilizing big data and Machine Learning (ML) is one of the
way to remain updated and gives us a strong deterrent
mechanism with which to minimize cyber hacking
attempts.
Gain insights and alerts from machine learning techniques
that go far beyond static thresholds and traditional
dashboards. Predict issues before they become major
ones.
Flag suspicious transactions. This is when some fraud
can’t be proven or money laundering cant be proven but
it is still suspicious. decrease fraud incidents and
increase your technology arsenal against hacking
efforts through machine learning.
Anomaly Detection
Machine learning algorithms learn the normal behavior of your business data in order to identify and
alert on anomalies and on what is abnormal. Anomalies aren’t categorically good or bad, they’re just
deviations from the expected value for a metric at any given point in time.
You can’t correctly attribute a specific anomaly to the underlying business incident if you don’t know
about anomalies to begin with (both good and bad anomalies). And that’s one of the main reasons
companies need anomaly detection: to get accurate feedback on the effectiveness of business
initiatives so that money and manpower can be utilized much more efficiently and to greater impact
for a company’s bottom line. Anomaly detection can point to positive business incidents as well as to
potential disasters.
The Silver Lining; but not the
magical cure for everything
– It's important to specify what machine learning is not:
– Big Data and ML is not a magic bullet to cure all hacking. There is no such thing
as ‘unhackable’. Even the best organizations and the most secretive ones like
CIA, NSA, Facebook, Microsoft, Uber get hacked.
– There are always human factors in place as well.
– Hacking won’t stop; it will only get worse as technology increases. As we
modernize over the future digital trends and hence financial consequences of
hacking will only increase. Digital trends are quickly becoming mainstream like
more online transactions, availing crypto-currencies like bitcoin, quantum
computers and is only projected to exponentially change our lifestyles.
– When there is a will, there is a way; hackers will continue inventing and finding
out new ways to exploit our customers. Banks must stay updated on technology
to minimize hacking to safeguard customer trust in their organization.
– Even when quantum computers will become a reality, there won’t be any
internet or online service that is ‘unhackable’. Classical cryptography will
become obsolete yes but will be replaced by quantum cryptography and new
ways of to hack and stop hacking.

More Related Content

What's hot

Security Compliance Models- Checklist v. Framework
Security Compliance Models- Checklist v. FrameworkSecurity Compliance Models- Checklist v. Framework
Security Compliance Models- Checklist v. FrameworkDivya Kothari
 
Weak Links: Cyber Attacks in the News & How to Protect Your Assets
Weak Links: Cyber Attacks in the News & How to Protect Your AssetsWeak Links: Cyber Attacks in the News & How to Protect Your Assets
Weak Links: Cyber Attacks in the News & How to Protect Your Assets
OilPriceInformationService
 
Holiday Season Fraud Forecast
Holiday Season Fraud ForecastHoliday Season Fraud Forecast
Holiday Season Fraud Forecast
Zachary Shaw
 
Secure Payments: How Card Issuers and Merchants Can Stay Ahead of Fraudsters
Secure Payments: How Card Issuers and Merchants Can Stay Ahead of FraudstersSecure Payments: How Card Issuers and Merchants Can Stay Ahead of Fraudsters
Secure Payments: How Card Issuers and Merchants Can Stay Ahead of Fraudsters
Cognizant
 
2015 CEB Tower Group Mar2015
2015 CEB Tower Group Mar20152015 CEB Tower Group Mar2015
2015 CEB Tower Group Mar2015
Ajay Alex
 
Sas wp enterrprise fraud management
Sas wp enterrprise fraud managementSas wp enterrprise fraud management
Sas wp enterrprise fraud management
rkappear
 
Detecting Wire Fraud in Real-Time
Detecting Wire Fraud in Real-TimeDetecting Wire Fraud in Real-Time
Detecting Wire Fraud in Real-Time
Laurent Pacalin
 
Fraud Management Solutions
Fraud Management SolutionsFraud Management Solutions
Fraud Management Solutions
SAS Institute India Pvt. Ltd
 
Global Identity Fraud Report 2020
Global Identity Fraud Report 2020Global Identity Fraud Report 2020
Global Identity Fraud Report 2020
Shufti Pro
 
Fraud Presentation
Fraud PresentationFraud Presentation
Fraud Presentationmbachnak
 
Findings from India Fraud Survey 2012: Fraud and Corporate Governance - Chang...
Findings from India Fraud Survey 2012: Fraud and Corporate Governance - Chang...Findings from India Fraud Survey 2012: Fraud and Corporate Governance - Chang...
Findings from India Fraud Survey 2012: Fraud and Corporate Governance - Chang...
EY
 
Fraud An International Perspective
Fraud   An International PerspectiveFraud   An International Perspective
Fraud An International Perspective
Steve Mitchinson
 
FRISS_Insurance fraud report 2020
FRISS_Insurance fraud report 2020 FRISS_Insurance fraud report 2020
FRISS_Insurance fraud report 2020
FinTech Belgium
 
Driving Payment Innovation - Know Your Enemy
Driving Payment Innovation - Know Your EnemyDriving Payment Innovation - Know Your Enemy
Driving Payment Innovation - Know Your Enemy
First Atlantic Commerce
 
FIS article - FFIEC Cybersecurity Assessment - by Andy Kim - Summer 2015
FIS article - FFIEC Cybersecurity Assessment - by Andy Kim - Summer 2015FIS article - FFIEC Cybersecurity Assessment - by Andy Kim - Summer 2015
FIS article - FFIEC Cybersecurity Assessment - by Andy Kim - Summer 2015Andy Kim
 
Online Identity Theft: Changing the Game
Online Identity Theft: Changing the GameOnline Identity Theft: Changing the Game
Online Identity Theft: Changing the Game
- Mark - Fullbright
 
Fraud Detection presentation
Fraud Detection presentationFraud Detection presentation
Fraud Detection presentation
Hernan Huwyler
 
RIB Cybersecurity
RIB CybersecurityRIB Cybersecurity
RIB CybersecurityAndy Kim
 
How to Build a Fraud Detection Solution with Neo4j
How to Build a Fraud Detection Solution with Neo4jHow to Build a Fraud Detection Solution with Neo4j
How to Build a Fraud Detection Solution with Neo4j
Neo4j
 

What's hot (19)

Security Compliance Models- Checklist v. Framework
Security Compliance Models- Checklist v. FrameworkSecurity Compliance Models- Checklist v. Framework
Security Compliance Models- Checklist v. Framework
 
Weak Links: Cyber Attacks in the News & How to Protect Your Assets
Weak Links: Cyber Attacks in the News & How to Protect Your AssetsWeak Links: Cyber Attacks in the News & How to Protect Your Assets
Weak Links: Cyber Attacks in the News & How to Protect Your Assets
 
Holiday Season Fraud Forecast
Holiday Season Fraud ForecastHoliday Season Fraud Forecast
Holiday Season Fraud Forecast
 
Secure Payments: How Card Issuers and Merchants Can Stay Ahead of Fraudsters
Secure Payments: How Card Issuers and Merchants Can Stay Ahead of FraudstersSecure Payments: How Card Issuers and Merchants Can Stay Ahead of Fraudsters
Secure Payments: How Card Issuers and Merchants Can Stay Ahead of Fraudsters
 
2015 CEB Tower Group Mar2015
2015 CEB Tower Group Mar20152015 CEB Tower Group Mar2015
2015 CEB Tower Group Mar2015
 
Sas wp enterrprise fraud management
Sas wp enterrprise fraud managementSas wp enterrprise fraud management
Sas wp enterrprise fraud management
 
Detecting Wire Fraud in Real-Time
Detecting Wire Fraud in Real-TimeDetecting Wire Fraud in Real-Time
Detecting Wire Fraud in Real-Time
 
Fraud Management Solutions
Fraud Management SolutionsFraud Management Solutions
Fraud Management Solutions
 
Global Identity Fraud Report 2020
Global Identity Fraud Report 2020Global Identity Fraud Report 2020
Global Identity Fraud Report 2020
 
Fraud Presentation
Fraud PresentationFraud Presentation
Fraud Presentation
 
Findings from India Fraud Survey 2012: Fraud and Corporate Governance - Chang...
Findings from India Fraud Survey 2012: Fraud and Corporate Governance - Chang...Findings from India Fraud Survey 2012: Fraud and Corporate Governance - Chang...
Findings from India Fraud Survey 2012: Fraud and Corporate Governance - Chang...
 
Fraud An International Perspective
Fraud   An International PerspectiveFraud   An International Perspective
Fraud An International Perspective
 
FRISS_Insurance fraud report 2020
FRISS_Insurance fraud report 2020 FRISS_Insurance fraud report 2020
FRISS_Insurance fraud report 2020
 
Driving Payment Innovation - Know Your Enemy
Driving Payment Innovation - Know Your EnemyDriving Payment Innovation - Know Your Enemy
Driving Payment Innovation - Know Your Enemy
 
FIS article - FFIEC Cybersecurity Assessment - by Andy Kim - Summer 2015
FIS article - FFIEC Cybersecurity Assessment - by Andy Kim - Summer 2015FIS article - FFIEC Cybersecurity Assessment - by Andy Kim - Summer 2015
FIS article - FFIEC Cybersecurity Assessment - by Andy Kim - Summer 2015
 
Online Identity Theft: Changing the Game
Online Identity Theft: Changing the GameOnline Identity Theft: Changing the Game
Online Identity Theft: Changing the Game
 
Fraud Detection presentation
Fraud Detection presentationFraud Detection presentation
Fraud Detection presentation
 
RIB Cybersecurity
RIB CybersecurityRIB Cybersecurity
RIB Cybersecurity
 
How to Build a Fraud Detection Solution with Neo4j
How to Build a Fraud Detection Solution with Neo4jHow to Build a Fraud Detection Solution with Neo4j
How to Build a Fraud Detection Solution with Neo4j
 

Similar to Big data analytical driven fraud detection for finance; banks and insurance

ATM Fraud Prevention Management White Paper from ESQ
 ATM Fraud Prevention Management White Paper from ESQ ATM Fraud Prevention Management White Paper from ESQ
ATM Fraud Prevention Management White Paper from ESQ
ESQ Business Services
 
TECH CYBER CRIME Homegrown menace Contents1. Regional trouble.docx
TECH CYBER CRIME Homegrown menace Contents1. Regional trouble.docxTECH CYBER CRIME Homegrown menace Contents1. Regional trouble.docx
TECH CYBER CRIME Homegrown menace Contents1. Regional trouble.docx
erlindaw
 
Artificial Intelligence in Banking
Artificial Intelligence in BankingArtificial Intelligence in Banking
Artificial Intelligence in Banking
Khawar Nehal khawar.nehal@atrc.net.pk
 
Artificial Intelligence in Banking
Artificial Intelligence in BankingArtificial Intelligence in Banking
Artificial Intelligence in Banking
Khawar Nehal khawar.nehal@atrc.net.pk
 
Economic offenses through Credit Card Frauds Dissected
Economic offenses through Credit Card Frauds DissectedEconomic offenses through Credit Card Frauds Dissected
Economic offenses through Credit Card Frauds Dissectedamiable_indian
 
Harshad - Economic offenses through Credit Card Frauds Dissected - ClubHack2008
Harshad - Economic offenses through Credit Card Frauds Dissected - ClubHack2008Harshad - Economic offenses through Credit Card Frauds Dissected - ClubHack2008
Harshad - Economic offenses through Credit Card Frauds Dissected - ClubHack2008ClubHack
 
TRANSFORMATION - BANKING INDUSTRY.pdf
TRANSFORMATION - BANKING INDUSTRY.pdfTRANSFORMATION - BANKING INDUSTRY.pdf
TRANSFORMATION - BANKING INDUSTRY.pdf
Ceyhun Jay Tugcu
 
State of Cyber Crime Safety and Security in Banking
State of Cyber Crime Safety and Security in BankingState of Cyber Crime Safety and Security in Banking
State of Cyber Crime Safety and Security in Banking
IJSRED
 
Not Prepared for Hacks .docx
                 Not Prepared for Hacks    .docx                 Not Prepared for Hacks    .docx
Not Prepared for Hacks .docx
hallettfaustina
 
Automated anti money laundering using artificial intelligence and machine lea...
Automated anti money laundering using artificial intelligence and machine lea...Automated anti money laundering using artificial intelligence and machine lea...
Automated anti money laundering using artificial intelligence and machine lea...
Santhosh L
 
Running head HOW TO AVOID INTERNET SCAMS AT THE WORKPLACE 1 .docx
Running head HOW TO AVOID INTERNET SCAMS AT THE WORKPLACE  1 .docxRunning head HOW TO AVOID INTERNET SCAMS AT THE WORKPLACE  1 .docx
Running head HOW TO AVOID INTERNET SCAMS AT THE WORKPLACE 1 .docx
wlynn1
 
CRC Alert November 2019 Final.pdf
CRC Alert November 2019 Final.pdfCRC Alert November 2019 Final.pdf
CRC Alert November 2019 Final.pdf
ssuser7464571
 
The Digital Identity Network -- A Holistic Approach to Managing Risk in a Glo...
The Digital Identity Network -- A Holistic Approach to Managing Risk in a Glo...The Digital Identity Network -- A Holistic Approach to Managing Risk in a Glo...
The Digital Identity Network -- A Holistic Approach to Managing Risk in a Glo...
Elizabeth Dimit
 
Do you have an identity theft protection plan
Do you have an identity theft protection planDo you have an identity theft protection plan
Do you have an identity theft protection plan
Angela Carrier- Founder, Business Leader Forum
 
Internet Threats and Risk Mitigation
Internet Threats and Risk MitigationInternet Threats and Risk Mitigation
Internet Threats and Risk Mitigation
BrandProtect
 
Credit Card Fraud Detection System Using Machine Learning Algorithm
Credit Card Fraud Detection System Using Machine Learning AlgorithmCredit Card Fraud Detection System Using Machine Learning Algorithm
Credit Card Fraud Detection System Using Machine Learning Algorithm
IRJET Journal
 
Leveraging Analytics to Combat Digital Fraud in Financial Organizations
Leveraging Analytics to Combat Digital Fraud in Financial OrganizationsLeveraging Analytics to Combat Digital Fraud in Financial Organizations
Leveraging Analytics to Combat Digital Fraud in Financial Organizations
Ricardo Ponce
 
Employer 0409
Employer 0409Employer 0409
Employer 0409
dgade
 
Accenture re-organizing-todays-cyber-threats
Accenture re-organizing-todays-cyber-threatsAccenture re-organizing-todays-cyber-threats
Accenture re-organizing-todays-cyber-threats
Lapman Lee ✔
 

Similar to Big data analytical driven fraud detection for finance; banks and insurance (20)

ATM Fraud Prevention Management White Paper from ESQ
 ATM Fraud Prevention Management White Paper from ESQ ATM Fraud Prevention Management White Paper from ESQ
ATM Fraud Prevention Management White Paper from ESQ
 
TECH CYBER CRIME Homegrown menace Contents1. Regional trouble.docx
TECH CYBER CRIME Homegrown menace Contents1. Regional trouble.docxTECH CYBER CRIME Homegrown menace Contents1. Regional trouble.docx
TECH CYBER CRIME Homegrown menace Contents1. Regional trouble.docx
 
Artificial Intelligence in Banking
Artificial Intelligence in BankingArtificial Intelligence in Banking
Artificial Intelligence in Banking
 
Artificial Intelligence in Banking
Artificial Intelligence in BankingArtificial Intelligence in Banking
Artificial Intelligence in Banking
 
ATM2.pdf.pdf
ATM2.pdf.pdfATM2.pdf.pdf
ATM2.pdf.pdf
 
Economic offenses through Credit Card Frauds Dissected
Economic offenses through Credit Card Frauds DissectedEconomic offenses through Credit Card Frauds Dissected
Economic offenses through Credit Card Frauds Dissected
 
Harshad - Economic offenses through Credit Card Frauds Dissected - ClubHack2008
Harshad - Economic offenses through Credit Card Frauds Dissected - ClubHack2008Harshad - Economic offenses through Credit Card Frauds Dissected - ClubHack2008
Harshad - Economic offenses through Credit Card Frauds Dissected - ClubHack2008
 
TRANSFORMATION - BANKING INDUSTRY.pdf
TRANSFORMATION - BANKING INDUSTRY.pdfTRANSFORMATION - BANKING INDUSTRY.pdf
TRANSFORMATION - BANKING INDUSTRY.pdf
 
State of Cyber Crime Safety and Security in Banking
State of Cyber Crime Safety and Security in BankingState of Cyber Crime Safety and Security in Banking
State of Cyber Crime Safety and Security in Banking
 
Not Prepared for Hacks .docx
                 Not Prepared for Hacks    .docx                 Not Prepared for Hacks    .docx
Not Prepared for Hacks .docx
 
Automated anti money laundering using artificial intelligence and machine lea...
Automated anti money laundering using artificial intelligence and machine lea...Automated anti money laundering using artificial intelligence and machine lea...
Automated anti money laundering using artificial intelligence and machine lea...
 
Running head HOW TO AVOID INTERNET SCAMS AT THE WORKPLACE 1 .docx
Running head HOW TO AVOID INTERNET SCAMS AT THE WORKPLACE  1 .docxRunning head HOW TO AVOID INTERNET SCAMS AT THE WORKPLACE  1 .docx
Running head HOW TO AVOID INTERNET SCAMS AT THE WORKPLACE 1 .docx
 
CRC Alert November 2019 Final.pdf
CRC Alert November 2019 Final.pdfCRC Alert November 2019 Final.pdf
CRC Alert November 2019 Final.pdf
 
The Digital Identity Network -- A Holistic Approach to Managing Risk in a Glo...
The Digital Identity Network -- A Holistic Approach to Managing Risk in a Glo...The Digital Identity Network -- A Holistic Approach to Managing Risk in a Glo...
The Digital Identity Network -- A Holistic Approach to Managing Risk in a Glo...
 
Do you have an identity theft protection plan
Do you have an identity theft protection planDo you have an identity theft protection plan
Do you have an identity theft protection plan
 
Internet Threats and Risk Mitigation
Internet Threats and Risk MitigationInternet Threats and Risk Mitigation
Internet Threats and Risk Mitigation
 
Credit Card Fraud Detection System Using Machine Learning Algorithm
Credit Card Fraud Detection System Using Machine Learning AlgorithmCredit Card Fraud Detection System Using Machine Learning Algorithm
Credit Card Fraud Detection System Using Machine Learning Algorithm
 
Leveraging Analytics to Combat Digital Fraud in Financial Organizations
Leveraging Analytics to Combat Digital Fraud in Financial OrganizationsLeveraging Analytics to Combat Digital Fraud in Financial Organizations
Leveraging Analytics to Combat Digital Fraud in Financial Organizations
 
Employer 0409
Employer 0409Employer 0409
Employer 0409
 
Accenture re-organizing-todays-cyber-threats
Accenture re-organizing-todays-cyber-threatsAccenture re-organizing-todays-cyber-threats
Accenture re-organizing-todays-cyber-threats
 

Recently uploaded

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
 
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdfCh03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
haila53
 
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Subhajit Sahu
 
Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)
TravisMalana
 
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
nscud
 
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
Tiktokethiodaily
 
standardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhstandardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghh
ArpitMalhotra16
 
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdfSample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Linda486226
 
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
Boston 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
 
一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单
ewymefz
 
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
 
Investigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_CrimesInvestigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_Crimes
StarCompliance.io
 
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
yhkoc
 
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdfCriminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP
 
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
vcaxypu
 
The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...
jerlynmaetalle
 
Jpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization SampleJpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization Sample
James Polillo
 
Best best suvichar in gujarati english meaning of this sentence as Silk road ...
Best best suvichar in gujarati english meaning of this sentence as Silk road ...Best best suvichar in gujarati english meaning of this sentence as Silk road ...
Best best suvichar in gujarati english meaning of this sentence as Silk road ...
AbhimanyuSinha9
 
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
NABLAS株式会社
 

Recently uploaded (20)

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
 
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdfCh03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
 
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
 
Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)
 
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
 
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
 
standardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhstandardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghh
 
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdfSample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
 
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
 
一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单
 
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
一比一原版(UofM毕业证)明尼苏达大学毕业证成绩单
 
Investigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_CrimesInvestigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_Crimes
 
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
 
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdfCriminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdf
 
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
 
The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...
 
Jpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization SampleJpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization Sample
 
Best best suvichar in gujarati english meaning of this sentence as Silk road ...
Best best suvichar in gujarati english meaning of this sentence as Silk road ...Best best suvichar in gujarati english meaning of this sentence as Silk road ...
Best best suvichar in gujarati english meaning of this sentence as Silk road ...
 
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
 

Big data analytical driven fraud detection for finance; banks and insurance

  • 1. Big Data Analytical Driven Fraud Detection for Finance- Banking and Insurance
  • 2.  Customer data security is one of the biggest challenges that banks the world over face. A few numbers show how significant this risk is:  The Nilson Report estimates that in 2016, losses topped USD 24.71 billion. That represents a 12% increase over the previous year.  According to a report from Javelin Strategy, there's a new identity theft victim every two seconds, and many of the incidents involve credit cards.  ACI Worldwide (an electronic payment systems company) estimates that 46% of Americans have had their card information compromised at some point in the past 5 years.  Approximately 65% of the time, credit card fraud results in a direct or indirect financial loss for the victim.  Among victims who reported direct financial losses, the average was $7,761 and the median was $2,000 per victim. This is compared with those who suffered indirect losses with an average of $261 and median of $10.  23 frightening credit card statistics: Feb 1, 2017; Rebecca Lake; Available at: https://www.creditdonkey.com/credit-card-fraud-statistics.html
  • 3.  Fraud accounts for 5-10 percent of claims costs for U.S. and Canadian insurers. Nearly one-third of insurers (32 percent) say fraud was as high as 20 percent of claims costs;  57 percent of insurers predict an increase in personal-property fraud by policyholders. Around 58 percent say the same for personal auto insurance, and 69 percent expect a rise in workers-compensation scams;  61 percent predict an increase in auto-insurance fraud by organized rings, and 55 percent predict an increase workers-compensation scamming;  About 35 percent say fraud costs their companies 5-10 percent of claim volume. More than 30 percent say fraud losses cost 10-20 percent of claim volume;  Detecting fraud before claims are paid, and upgrading analytics, were mentioned most often as the insurers’ main fraud-fighting priorities; and  One-third of insurers don’t feel adequately protected against fraud. (FICO, August 2013)  Insurance fraud statistics: Available at: http://www.insurancefraud.org/statistics.htm#2
  • 4.  Insurance companies lose an estimated $30 billion per year in insurance fraud costs that have to get passed on to bill-paying consumers.  The most common types of insurance fraud are:  1) Stolen car  2) car accident  3) car damage  4)health insurance billing fraud  5) unnecessary medical procedures  6) staged home fires  7) storm fraud  8) abandoned house fire  9)faked death  10) renter’s insurance  Insurance fraud statistics: Available at: http://www.insurancefraud.org/statistics.htm#2
  • 5.  Customer data security is one of the biggest challenges that banks the world over face but Pakistani banks have now become even more vulnerable. A few quotes highlight why:  “We not only face threats from hackers who skim ATMs or manipulate online accounts just for swindling money, but also from organised hacking groups whose objectives are wider,”- the head of a local bank.  “Pakistan’s entire security establishment is walking a tight rope after entering into the CPEC [China-Pakistan Economic Corridor]. Foreign powers are making every effort to embarrass the country. We need to thoroughly investigate the real motives behind the recent skimming in the light of previous bank data stealing incidents in which some Chinese nationals were involved,” a well-placed source in the FIA  Over the years, the use of ATMs has been growing rapidly in Pakistan. According to SBP statistics, about 110m ATM transactions took place in just the nine months from July 2016 to March 2017, with the total value of these transactions exceeding Rs960 billion. As banks continue to encourage their clients to use ATMs and as people experience the benefits doing so, these numbers are only poised to grow.
  • 6.  In the current spree of ATM skimming, 296 customers of HBL have so far confirmed being defrauded, an aggregate loss of PKR 10.2m, implied a press release issued by the State Bank of Pakistan (SBP) on Dec 5. The number of bank accounts affected, though, is around 600, according to newspaper reports.  Apart from this, several such cases have been reported from Dolmen Mall, Karachi. Reports also surfaced of a similar cyberattack in Islamabad. Banks including HBL responded by blocking users’ ATM cards as a precaution against further loss.  Rising Prevalence of ATM Fraud; Dec 11,2017; Dawn; Available at: https://www.dawn.com/news/1375856  Beware- Hackers are going after ATMs in Pakistan: Salman Siddiqui, Dec 3, 2017: The Express Tribune: Available at: https://tribune.com.pk/story/1574702/2-beware-hackers-going-atms- pakistan/
  • 7.  The National Accountability Bureau (NAB) on Saturday arrested 23 accused officials of State Life Insurance Corporation, including a regional manager, in a scam of over Rs 100 million related to bogus policies. According to a NAB spokesman, the accused caused the heavy loss through bogus insurance policies by opening 113 bank accounts and withdrawing cash against over 430 cheques. He said the accused officials facilitated fake policies to around 90 individuals who had never entered into any policy with State Life Insurance. He said a local government councillor was also among the arrested accused.  Inflated health claims, stolen cars, money laundering and fraud through life insurance is common but not properly analyzed and quantified. Central databases need to be made by SECP regulator too.  NAB arrests 23 officers in PKR 100 million insurance scam; April 17,2017; The News; Available at:https://www.thenews.com.pk/print/199063-NAB-arrests-23-officers-in-Rs-100m- insurance-scam
  • 8. Culture Level Soft Facts Organizational Level 90% of the problems caused by hacking remain undetected and hidden Hard Facts Only 10% of the problems caused by hacking are brought onto the surface Top leadership Board of Directors driven initiative is key to establishing comprehensive Cyber crime division in the bank.
  • 9. Availing latest technology and analytics Handling situations correctly by the bank and insurer Big Data Neural Networks Machine Learning Anomaly Detection KPIs holistic; key metrices Clustering Deep Learning Fraud Analytics Customer support and awareness Forensic IT Handling situations holistically PR and Customer perception handling Preparing contingency plans for hacking Holistically combating fraud Deep Learning is based on neural networks which mimic how our brain and neurons work. Big Data and Machine Learning Analytics
  • 10. Big Data and Machine Learning Analytics Being hacked is an inevitable fact of life and normal way of doing business now. What matters now is how we handle the crises when it occurs, and how much pre- emptive preparations we take to minimize hacking attempts. It’s important to remain at level with hackers on technology and to utilize new technologies so that we remain at the forefront of all cyber issues Utilizing big data and Machine Learning (ML) is one of the way to remain updated and gives us a strong deterrent mechanism with which to minimize cyber hacking attempts. Gain insights and alerts from machine learning techniques that go far beyond static thresholds and traditional dashboards. Predict issues before they become major ones. Flag suspicious transactions. This is when some fraud can’t be proven or money laundering cant be proven but it is still suspicious. decrease fraud incidents and increase your technology arsenal against hacking efforts through machine learning.
  • 11. Anomaly Detection Machine learning algorithms learn the normal behavior of your business data in order to identify and alert on anomalies and on what is abnormal. Anomalies aren’t categorically good or bad, they’re just deviations from the expected value for a metric at any given point in time. You can’t correctly attribute a specific anomaly to the underlying business incident if you don’t know about anomalies to begin with (both good and bad anomalies). And that’s one of the main reasons companies need anomaly detection: to get accurate feedback on the effectiveness of business initiatives so that money and manpower can be utilized much more efficiently and to greater impact for a company’s bottom line. Anomaly detection can point to positive business incidents as well as to potential disasters.
  • 12. The Silver Lining; but not the magical cure for everything – It's important to specify what machine learning is not: – Big Data and ML is not a magic bullet to cure all hacking. There is no such thing as ‘unhackable’. Even the best organizations and the most secretive ones like CIA, NSA, Facebook, Microsoft, Uber get hacked. – There are always human factors in place as well. – Hacking won’t stop; it will only get worse as technology increases. As we modernize over the future digital trends and hence financial consequences of hacking will only increase. Digital trends are quickly becoming mainstream like more online transactions, availing crypto-currencies like bitcoin, quantum computers and is only projected to exponentially change our lifestyles. – When there is a will, there is a way; hackers will continue inventing and finding out new ways to exploit our customers. Banks must stay updated on technology to minimize hacking to safeguard customer trust in their organization. – Even when quantum computers will become a reality, there won’t be any internet or online service that is ‘unhackable’. Classical cryptography will become obsolete yes but will be replaced by quantum cryptography and new ways of to hack and stop hacking.