Fighting financial fraud at Danske Bank with artificial intelligence
•
17 likes•8,014 views
Danske Bank, the leader in mobile payments in Denmark, is innovating with AI. Danske Bank’s existing fraud detection engine is being enhanced with deep learning algorithms that can analyze potentially tens of thousands of latent features. Danske Bank’s current system is largely based on handcrafted rules created by the business, based on intuition and some light analysis. The system is effective at blocking fraud, but it has a high rate of false positives, which is expensive and inconvenient, and it has proved impractical to update and maintain as fraudsters evolve their capabilities. Moreover, the bank understands that fraud is getting worse in the near- and long-term future due to the increased digitization of banking and the prevalence of mobile banking applications and recognizes the need to use cutting-edge techniques to engage fraudsters not where they are today but where they will be tomorrow. Application fraud is an important emerging trend, in which machines fill in transaction forms. There is evidence that criminals are employing sophisticated machine-learning techniques to attack, so it’s critical to use sophisticated machine learning to catch fraud in banking and mobile payment transactions. Ron Bodkin and Nadeem Gulzar explore how Danske Bank uses deep learning for better fraud detection. Danske Bank’s multistep program first productionizes “classic” machine learning techniques (boosted decision trees) while in parallel developing deep learning models with TensorFlow as a “challenger” to test. The system was first tested in shadow production and then in full production in a champion-challenger setup against live transactions. Ron and Nadeem explain how the bank is integrating the models with the efforts already running, giving the bank and its investigation team the ability to adapt to new patterns faster than before and taking on complex highly varying functions not present in the training examples.
Recommended
Recommended
More Related Content
What's hot
What's hot (20)
Similar to Fighting financial fraud at Danske Bank with artificial intelligence
Similar to Fighting financial fraud at Danske Bank with artificial intelligence (20)
Recently uploaded
Recently uploaded (20)
Fighting financial fraud at Danske Bank with artificial intelligence
- 1. 1 Fighting Financial Fraud with Artificial Intelligence © 2017 Teradata
- 2. 2 Ron Bodkin VP & GM, Artificial Intelligence, Teradata @ronbodkin Nadeem Gulzar Head of Global Analytics, Danske Bank @Nadeem_Gulzar
- 3. 3 So far we have delivered 150+ successful projects for 100+ clients worldwide. 500+ employees (2017) Vendor-neutral with an open source focus. Full spectrum consulting, data engineering, data science & support. Apache Hadoop and cloud ecosystem integration. Founded in 2010 industry thought leader. Fixed fee offerings for data science and engineering. Who Is Think Big? 1st Big Data provider 100% focused around open source.
- 4. 4 We help our customers be financially confident and achieve their ambitions by making daily banking and important financial decisions easy. 19,000 employees (2017) 1,800 corporate and institutional customers Danske Bank covers all Personal Banking, Business Banking, Corporates & Institutions and Wealth Management. 2.7 million personal customers 236,000 small and medium-sized business customers Making banking easier for over 145 years. Who Is Danske Bank? Danske Bank is a Nordic universal bank with strong local roots and bridges to the rest of the world
- 5. 5 Data Driven Approach to Fight Fraud Challenges for Fraud Detection • Low Detection Rate • Many False Positives • High Fraud Loss • Fast Growing Competition Ambitions for Fraud Project Danske Bank advanced analytics blueprint Data driven approach to real time scoring of transactions Reduce false-positives & Enhance fraud detection rate
- 6. 6 Data Driven Approach to Fight Fraud Fast evolving fraud sophistication Ambitions for Fraud Project Danske Bank advanced analytics blueprint Data driven approach to real time scoring of transactions Reduce false-positives & Enhance fraud detection rate ONLY ~40% of fraud cases are detected Low Detection Rate 99.5% of cases are not fraud related Many false positives Challenges for Fraud Detection Tens of Millions € lost each month High Fraud Loss © 2017 Teradata
- 7. 7 Fraud Types – Customer Initiated Nigeria/ Investment Scam CEO Fraud Customer Initiated © 2017 Teradata Beneficiary Account Change Fake Invoice Rental Scam/ Goods Not Received
- 8. 8 ID Theft SPEAR Phishing Vishing/Support Scam Malware Phishing/Smishing Fraud Types – Fraudster Initiated Fraudster Initiated © 2017 Teradata
- 9. 9 Modeling Challenges © 2017 Teradata • Class imbalance (100,000:1 non-fraud vs. fraud) • Assigning fraud labels from historic data • Fraud is ambiguous • Not all features available in real-time • Most machine learning sees transactions atomically
- 10. 10 Advanced Platform for Fraud: Data-Driven Approach How It Works: • Understanding the domain • Gathering and preparing the data • Automatically generating the rules and recognizing fraudulent patterns by training models on historical data • Automatically maintaining the engine by retraining the model Pros: • Automatic/data-driven/objective inference of the rules • Ability to detect patterns in a high dimensional data input • Fast detection of new/changing fraudulent patterns Cons: • Might be unintuitive and hardly interpretable • Data preparation and feature aggregation is time consuming © 2017 Teradata
- 11. 11 Phase One © 2017 Teradata
- 12. 12 Sep Oct Nov Dec Jan Feb Mar Apr May Jun Jul Project kick-off 30th September Teamwork to Deliver Value in Each Project Iteration 2016 2017 Kick-off: Data Scientist track Go-Live plan set for the project 19th December Kick-off: Engineering track Models successfully in Shadow Production 4th March First round trip test transaction First production virtual machine Production Hardening for HA and Security Full productionisation of the Fraud Engine Cross-functional Collaboration Cont. Deep Learning modeling © 2017 Teradata
- 13. 13 > Banking Anti-Fraud Solution © 2017 Teradata Banking Anti-Fraud Solution By leveraging the power of a thoughtful and strong data and analytics strategy, we unleash high impact business outcomes. • Multiple models running in production at the same time • Mix of traditional and advance deep learning methods • AnalyticsOps: Deploying machine learning models in production Model Management Framework • Organisation and silos of data • Real-time data integration • Security and Procedures: following existing bank procedures Data Modelling, Pipeline and Ingestion • Hard to operationalize insights • Availability of analytic capabilities/ skills and data • Interpreting the results of machine learning models Machine Learning and Artificial Intelligence
- 14. 14 Advanced Platform for Fraud: Data-Driven Approach Manual Evaluation eBanking Mobile Pay Business Online Global Payment Interface Fraud? Create Verification Fraud Payment Weblog Data Basic Customer Data Historic Transactions Customer Product Data Aggregated Customer Data Fraud? Advanced Analytics Platform for Fraud Central Fraud Engine Process Payment to Beneficiary Yes/Maybe No Yes ! Return Payment to Customer Update Fraud Data © 2017 Teradata No
- 15. 15 Model Management Real Time Scoring System Production Operations Source Systems Data Managers Framework to Enhance Danske Bank AnalyticsOps Capabilities Log Transactions Add Historic Data Model Performance Promote Models © 2017 Teradata Data Scientists Development & Deployment Management Data Science Lab Data Analysis & Model Development Data Management Developers & Release Managers
- 16. 16 Key Requirement: Model Interpretation • We have deployed LIME (Locally Interpretable Model Explanation) for customers – Improves trust – Compliance with EU’s General Data Protection Regulation (GDPR) © 2017 Teradata 17.6% Fraud Probability Customer Amount Debit Amount Avg. # Trans Cred Acc # Prev to This Dest # Xfer Accounts X% score due to: + transfer amount + destination country + last year monthly spend What features are most important to this decision?
- 17. 17 Machine Learning Results (Live System: 60 transactions/sec.) Ensemble of boosted decision trees and logistic regression. From online validation of the model: ● 25-30% false positive reduction, with over 35% increase in detection rate ● Opportunity to expand model with additional features, retrain on recent data and add additional models to the ensemble. ● Models can be expanded to additional channels Rule Engine on validation set © 2017 Teradata
- 18. 18 Deep Learning © 2017 Teradata
- 19. 19 Current models can only catch ~70% of all fraud cases Deep Learning Opportunity Traditional ML models view transactions atomically Often missed fraud transactions are part of a series Capturing correlation across many features © 2017 Teradata
- 20. 20 Three Deep Learning Architectures to Deliver Value • Designed for spatial correlated features, but by transforming transactions into a 2D image, we can learn temporal correlated features. • Deeper ConvNet allows learning more complex & general features. Goal: Learn kernels from temporal & static features to gain insight into the characteristics of fraud. • Learn temporal information and classify if the sequence of transactions contains fraud. • Shares knowledge across learning time. Goal: Learn transaction patterns within a window. Two solutions can be tested: flag fraud or predict next transaction and define an error. • Learn how to generate normal transactions, potentially large volumes of non-fraud data. • AE provide a low level representation of the data. Goal: Build a model that learns how to generate non-fraud data. To detect fraud, define a reconstruction error rate for the fraud cases Auto-Encoders LSTM ConvNet © 2017 Teradata
- 21. 21 How Can We Create an Image From Bank Transactions? t0 X_0, X_1, ... X_n dt t1 X_0, X_1, ... X_n t2 X_0, X_1, ... X_n ts X_0, X_1, ... X_n ... Top k Features Correlation ... X_0 X_41 X_5 X_30 X_29X_31X_10 X_37 X_3 X_1 X_42 X_40 X_32 X_15X_35X_2 X_16 X_31 X_2 X_3 X_15 X_4 X_1X_28X_40 X_31 X_49 X_n X_26 X_9 X_40 X_35X_28X_2 X_17 X_1 ... X_0 X_41 X_5 X_30 X_29X_31X_10 X_37 X_3 X_1 X_42 X_40 X_32 X_15X_35X_2 X_16 X_31 X_2 X_3 X_15 X_4 X_1X_28X_40 X_31 X_49 X_n X_26 X_9 X_40 X_35X_28X_2 X_17 X_1 ... ... ... ... ... X_0 X_41 X_5 X_30 X_29X_31X_10 X_37 X_3 X_1 X_42 X_40 X_32 X_15X_35X_2 X_16 X_31 X_2 X_3 X_15 X_4 X_1X_28X_40 X_31 X_49 X_n X_26 X_9 X_40 X_35X_28X_2 X_17 X_1 N dt t0 t1 ts Input Output Raw Features Add correlated features in a clock-wise manner © 2017 Teradata Image size is: [10 x 3, 50 x 3, 1]
- 22. 22 Convolutional Layers for Trans2D Kernels of 3x3 ...X_0 X_1 X_2 X_n ...X_0 X_1 X_2 X_n... ... ... ... ...X_0 X_1 X_2 X_n Features Time Strides of 3 Strides of 1 First Convolutional Layer Architecture © 2017 Teradata
- 23. 23 2D Transaction Image Example © 2017 Teradata Non-fraud Transaction Image Non-fraud Fraud Transaction Image X-axis: features, Y-axis: time Fraud Non-fraud
- 24. 24 Network Architecture for CNNs Fraud Normal 50 30 25 15 13 8CNN Fraud Normal50 30 25 15 25 15 25 15 25 15 © 2017 Teradata
- 25. 25 Inside the ResNet model 64 Filters Activations After the CNN Residual Blocks FraudNon-fraud © 2017 Teradata
- 26. 26 Deep Learning First Results on the fraud verification dataset Comparison of the three deep learning models andthe traditional machine learning ensemble model. © 2017 Teradata • Ensemble model (AUC 0.89) • ConvNets (AUC 0.95) • LSTM (AUC 0.90) • ResNet (AUC 0.94)
- 27. 27 Lessons Learned: Take-Aways From Danske Bank Deep learning adoption from pictures to financial transactions Enhancement of data quality & cluster capabilities with data ingestion Building Analytics Ops capabilities to support business units Leveraging experience from Fraud advanced analytics to deliver extra use cases © 2017 Teradata
- 28. 28 Success: From PowerPoint to production in 8 sprints Team effort: Thorough collaboration across IMD, GFU and Think Big Synergy: Successfully spearheaded innovation in all involved systems Inspiration: Incorporation Danske Bank advanced analytics blueprint sets a generic scene for combatting new challenges in advanced analytics Agile influence: Using an agile approach we were able to quickly deliver within the challenging timeframe. © 2017 Teradata Big Data Team – Lessons Learned
- 29. 29 Ron Bodkin VP & GM, Artificial Intelligence, Teradata @ronbodkin Nadeem Gulzar Head of Global Analytics, Danske Bank @Nadeem_Gulzar
- 31. 31 Advanced Analytics Fraud Platform • Develop a scalable and expandable platform which follows the Danske Bank blueprint of digitalization • 100 % data-driven approach to find patterns in the data and complement the existing fraud engine • Use Hadoop to handle the large data volumes for training models on transaction data • Implement a real-time solution that can score live transactions such as e-banking, credit card and mobile payments. • Reduce amount of false-positives by at least 20-40 % © 2017 Teradata
- 32. 32 Ambitions for the Advance Analytics project • The goal is to enhance fraud detection and reduce false positives across products. • Fraud is only the first of many possible advanced analytics use cases. • The project leads to the creation of Danske Bank advanced analytics blueprint. • Danske Bank ambition is to become one of the bank leading in advanced analytics capabilities. Challenges in Fraud Detection at Danske Bank • Low detection rate: Existing human-written rule engine catches ~40% of fraud cases. • Many false positives: 99.5% of all cases investigated are not fraud related. • High fraud loss: Tens of millions of € total fraud per month. • Mobile payments are quickly growing in number. • Fraud evolving rapidly, with increased sophistication: Danske Bank must modernize its anti-fraud arsenal. © 2017 Teradata