Data Analysis for Credit Card Fraud Detection
Description: Data Analysis for Credit Card Fraud Detection Alejandro Correa Bahnsen Luxembourg University Introduction Introduction Simplify transaction flow Fraud?? Network Introduction Database Evaluation of algorithms Logistic Regression Financial
Related Topics
Download Presentation
"Data Analysis for Credit Card Fraud Detection" is the property of its rightful owner. Permission is granted to download and print the materials on this website for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Presentation Transcript
slide1. Data Analysis for Credit Card Fraud Detection Alejandro Correa Bahnsen Luxembourg University<br>
slide2. Introduction<br>
slide3. Introduction<br>
slide4. Simplify transaction flow Fraud?? Network<br>
slide5. Introduction
Database
Evaluation of algorithms
Logistic Regression
Financial measure
Cost Sensitive Logistic Regression Agenda<br>
slide6. Database Larger European card processing company
2012 card present transactions
750,000 Transactions
3500 Frauds
0.467% Fraud rate
148,562 EUR lost due to fraud on test dataset Dec
Nov
Oct
Sep
Aug
Jul
Jun
May
Apr
Mar
Feb
Jan Test Train<br>
slide7. Raw attributes
Other attributes:
Age, country of residence, postal code, type of card Database 7<br>
slide8. Derived attributes
Combination of
following criteria: Database 8<br>
slide9. Evaluation Confusion matrix<br>
slide10. Introduction
Database
Evaluation of algorithms
Logistic Regression
Financial measure
Cost Sensitive Logistic Regression Agenda<br>
slide11. Model
Cost Function
Cost Matrix Logistic Regression<br>
slide12. 1% 5% 10% 20% 50% Logistic Regression Under sampling procedure 0.467% Select all the frauds and a random sample of the legitimate transactions.<br>
slide13. Logistic Regression Results<br>
slide14. Motivation
False positives carry a different cost than false negatives
Frauds range from few to thousands of euros (dollars, pounds, etc) Financial evaluation There is a need for a real comparison measure<br>
slide15. Cost matrix
where: Financial evaluation Ca Administrative costs
Amt Amount of transaction i Evaluation measure<br>
slide16. Logistic Regression Results Selecting the algorithm by F1-Score Selecting the algorithm by Cost<br>
slide17. Logistic Regression Best model selected using traditional F1-Score does not give the best results in terms of cost
Model selected by cost, is trained using less than 1% of the database, meaning there is a lot of information excluded
The algorithm is trained to minimize the miss-classification (approx.) but then is evaluated based on cost
Why not train the algorithm to minimize the cost instead?<br>
slide18. Cost Matrix Cost Sensitive Logistic Regression Cost Function<br>
slide19. Cost sensitive Logistic Regression Results<br>
slide20. Cost sensitive Logistic Regression Results<br>
slide21. Conclusion Selecting models based on traditional statistics does not give the best results in terms of cost
Models should be evaluated taking into account real financial costs of the application
Algorithms should be developed to incorporate those financial costs<br>
slide22. Thank you!<br>
slide23. Contact information Alejandro Correa Bahnsen
University of Luxembourg
Luxembourg
al.bahnsen@gmail.com
http://www.linkedin.com/in/albahnsen
http://www.slideshare.net/albahnsen<br>
slide2. Introduction<br>
slide3. Introduction<br>
slide4. Simplify transaction flow Fraud?? Network<br>
slide5. Introduction
Database
Evaluation of algorithms
Logistic Regression
Financial measure
Cost Sensitive Logistic Regression Agenda<br>
slide6. Database Larger European card processing company
2012 card present transactions
750,000 Transactions
3500 Frauds
0.467% Fraud rate
148,562 EUR lost due to fraud on test dataset Dec
Nov
Oct
Sep
Aug
Jul
Jun
May
Apr
Mar
Feb
Jan Test Train<br>
slide7. Raw attributes
Other attributes:
Age, country of residence, postal code, type of card Database 7<br>
slide8. Derived attributes
Combination of
following criteria: Database 8<br>
slide9. Evaluation Confusion matrix<br>
slide10. Introduction
Database
Evaluation of algorithms
Logistic Regression
Financial measure
Cost Sensitive Logistic Regression Agenda<br>
slide11. Model
Cost Function
Cost Matrix Logistic Regression<br>
slide12. 1% 5% 10% 20% 50% Logistic Regression Under sampling procedure 0.467% Select all the frauds and a random sample of the legitimate transactions.<br>
slide13. Logistic Regression Results<br>
slide14. Motivation
False positives carry a different cost than false negatives
Frauds range from few to thousands of euros (dollars, pounds, etc) Financial evaluation There is a need for a real comparison measure<br>
slide15. Cost matrix
where: Financial evaluation Ca Administrative costs
Amt Amount of transaction i Evaluation measure<br>
slide16. Logistic Regression Results Selecting the algorithm by F1-Score Selecting the algorithm by Cost<br>
slide17. Logistic Regression Best model selected using traditional F1-Score does not give the best results in terms of cost
Model selected by cost, is trained using less than 1% of the database, meaning there is a lot of information excluded
The algorithm is trained to minimize the miss-classification (approx.) but then is evaluated based on cost
Why not train the algorithm to minimize the cost instead?<br>
slide18. Cost Matrix Cost Sensitive Logistic Regression Cost Function<br>
slide19. Cost sensitive Logistic Regression Results<br>
slide20. Cost sensitive Logistic Regression Results<br>
slide21. Conclusion Selecting models based on traditional statistics does not give the best results in terms of cost
Models should be evaluated taking into account real financial costs of the application
Algorithms should be developed to incorporate those financial costs<br>
slide22. Thank you!<br>
slide23. Contact information Alejandro Correa Bahnsen
University of Luxembourg
Luxembourg
al.bahnsen@gmail.com
http://www.linkedin.com/in/albahnsen
http://www.slideshare.net/albahnsen<br>