slash n: technical session 7 - fraudsters are smart, frank is smarter - vivek mehta, fareed jawad
DESCRIPTION
TRANSCRIPT
![Page 1: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/1.jpg)
28/01/13 1
Fraudsters are smart, “Frank” is Smarter
- Fareed and Vivek
![Page 2: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/2.jpg)
2 of 22
Outline
Why detect fraud – Is there a problem?Why an intelligent system?How we built one
![Page 3: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/3.jpg)
Show me some numbers
What was the value of all electronic transactions globally for year 2012?
$17 trillion (with a T)This includes all credit, debit and pre-paid
cards used in both online and offline (card present) scenarios for purchases and cash withdrawals
![Page 4: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/4.jpg)
More Numbers
How much of $17T was lost due to FRAUD?$8 billion in 2012, > $10 billion by 2015 Fraud rate of 0.05% – Not too bad right?Wrong !!
![Page 5: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/5.jpg)
Getting specific
Reminder - 0.05% ratio is for all transactions including face to face transactions
The fraud rate is a much more scary 3.5% for Online transactions aka CNP
Global e-Commerce is expected to exceed $1T in 2013 –> $3.5B will be lost due to fraud
Add to this, the erosion due to loss of future business from impacted customers
Big Customer Impact ! Big deal for us !!
![Page 6: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/6.jpg)
The Big Fight...
Fraud to transaction ratio has been constant over the past 10 years
This ratio should not lull us into a false sense of security – bigger numbers are at stake and increasing as volumes grow
The crooks LOVE e-Commerce (think 3.5%)How do we then figure out if a transaction is
genuine or a victim of fraudIntelligently of course! - ENTER FRANK !!
![Page 7: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/7.jpg)
Why Frank?
![Page 8: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/8.jpg)
8 of 22
Fraud Detection System
Two partsSignals/FeaturesAlgorithm
![Page 9: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/9.jpg)
9 of 22
Rule based system
Rules on various signalsNum of transaction from a card in last one dayTransaction amountand many more
Thresholds are hand craftedFraud Score = sum of individual scores
![Page 10: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/10.jpg)
10 of 22
Need for Smarter system Too much data for manual analysis Businesses are evolving Fraudsters are evolving Extending to really high dimension – pushing
beyond limits of rule based system
![Page 11: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/11.jpg)
11 of 22
Designing Frank
Labeled data missingObservation
Very few fraud records
When you see one, you can identify one
Social behavior
![Page 12: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/12.jpg)
12 of 22
Visualization
Number of transactions in a day by a user
Total Amount
![Page 13: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/13.jpg)
13 of 22
Visualization
![Page 14: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/14.jpg)
14 of 22
Clustering – Centroid based
![Page 15: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/15.jpg)
15 of 22
Clustering - Distance based
![Page 16: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/16.jpg)
16 of 22
Clustering - Distribution based
![Page 17: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/17.jpg)
17 of 22
Clustering – Density based
![Page 18: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/18.jpg)
18 of 22
Density based clustering
p
qp1
EpsilonMin-ptsStatistical distance
Scale invariantCorrelation taken into
account
![Page 19: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/19.jpg)
19 of 22
Clustering for detecting fraud
Cluster the data using density based clusteringFor new point find distance to all the existing
clustersIf there exists min-pts with epsilon dist in a
cluster, new point belongs to this clusterIf doesn't belong to any cluster -> fraud
![Page 20: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/20.jpg)
20 of 22
Computing fraud probability
We find nearest clusterConvert the distance to probability
using chi-square distribution
Probability of fraud between 0 and 1
![Page 21: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/21.jpg)
21 of 22
Execution
Distributed clusteringReal-time model updating< 20ms to compute fraud probabilitySuspend the payment authorization in real
time
![Page 22: Slash n: Technical Session 7 - Fraudsters are smart, Frank is smarter - Vivek Mehta, Fareed Jawad](https://reader035.vdocument.in/reader035/viewer/2022070301/545d3adcaf7959b9098b4b56/html5/thumbnails/22.jpg)
22 of 22
We Frank, You Shop.