SlideShare a Scribd company logo
1 of 32
Download to read offline
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Using ML to detect and prevent fraud
without compromising user
experience
Christopher Marsh-Bourdon
Principle Solutions Architect
Amazon Web Services
F S V 3 0 2
Justin Fox
Head of Platform Innovation
NuData Security
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Agenda
What is NuDetect?
Layers of threat intelligence
Big-data processing
Let’s talk DataOps
Next steps
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Related breakouts
AIM304 – Machine learning for developers & data scientists with Amazon
SageMaker
Cyrus Vahid, AWS
AIM306 – Fraud detection using machine learning with Amazon SageMaker
Cyrus Vahid, AWS
AIM309 – Setting up custom machine learning environments on AWS
Shashank Prasanna, AWS
S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Let’s start with our history
NuData Security was born in the AWS Cloud
• Early adopters in 2007, on Amazon EC2 Classic
• As the cloud innovated we leveraged the advances
• VPC? Check. Config? Check. Lambda? Check.
Targeted identity verification to reduce fraud
• E-Commerce, Financial Institutions
• Focus on consumer experience, #frictionless
• Powered by machine learning
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
What does the landscape look like?
of payment executives at FIs believe that the evolution of
digital as a channel adds significant risk of fraud180%
of credit losses and 5 percent of charged-off accounts are
due to credit application fraud using synthetic identities3
Cybercrime is more
sophisticated than
ever and the costs
are mounting
As banking moves toward a more
digital experience with increased
points of interaction, it is more critical
than ever to accurately identify your
real customers from fraudulent
attempts to manage risk
1/3 of US businesses have had customer data breached2
cost of cybercrime to US issuers by 20194
$2 trillion
20%
1. LexisNexis, "True Cost of Fraud,” 2017 2. Javelin 2017 State of Authentication Report
3. Auriemma Consulting Group, "Synthetic
Identity Fraud Cost Lenders $6 Billion In
2016," August 2017
4. Forbes, “Cyber crime costs projected to
reach $2 trillion by 2019," 2016
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Why do we care?
Accurate authentication is critical, but it requires careful
balancing of security needs with a great user experience
#1
Identity verification is
among the top three
challenges facing financial
institutions1
36%
increase in incidence of
account takeover since 2015
and a 60 percent increase in
losses2
74%
of financial institutions state
that improving the
consumer experience is an
important component in a
business case for a new
fraud solution3
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
We combine layers of security
Device, connection,
and location
identification
Trust that the real consumer is
using the device.
Behavioral analytics
Continuously verify the
consumer. Trust the
behavior.
Passive (invisible)
biometric verification
Trust the consumer based on
natural behaviors and
sensory inputs.
Real-time trust
consortium
Aggregated, network-level data
from all behavioral interactions.
Trust the consortium.
S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Intro to our architecture
Systems evolve
Monolith
Microservices
Containers
Functions
Leverage managed services
Lower operational overhead
Acts as an interface between systems
Key principles
Creating a DevOps culture, teams own stuff
You made the model, you own it (end to end)
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
NuDetect architecture
Corporate data
center
AWS Cloud
Amazon CloudFront
AWS PrivateLinkAmazon VPC
AWS Cloud
AWS Global Accelerator Elastic Load
Balancing
Amazon EC2
AWS Lambda
Amazon ECS
Connectivity options Real-time scoring engine
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Microservice architecture
AWS Cloud
Real-time device intelligence
Real-time passive biometrics
Real-time trust consortium
Amazon DynamoDB
Amazon RDS
Amazon ElastiCache
Amazon API Gateway
Elastic Load Balancing
Elastic Load Balancing Amazon EC2
Lambda
Amazon ECS
S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
How much data do you need?
Big data is just another word for data hoarder
Every service generates data
Telemetry data/metrics
System logging
Application logging
Performance data
Let’s be real: More data equals more problems
Compliance
Regulations
Privacy
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Evolution of big data at NuData (part 1)
Data operations monitoring
Elastic Load
Balancing
Amazon EC2
ElastiCache
Amazon S3
Amazon Redshift
1
12
2
Amazon EC2
Spot Fleet
Amazon SNS Amazon CloudWatch Amazon EC2 Auto Scaling
AWS Cloud
Data processing workflow
Cassandra
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Evolution of big data at NuData (part 2)
Event aggregation workflow
Data operations monitoring
ElastiCache Amazon EC2 Elastic Load
Balancing
Amazon EC2
ElastiCache
Amazon S3
Amazon Redshift
1
12
2
Amazon EC2
Spot Fleet
Amazon SNS CloudWatch Amazon EC2 Auto Scaling
AWS Cloud
Data processing workflow
Cassandra
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Evolution of big data at NuData (part 3)
AWS Cloud
Event aggregation workflow
Data operations monitoring
Data processing workflow
ElastiCache Amazon EC2 Elastic Load
Balancing
Amazon EC2
ElastiCache
Amazon S3
Amazon Kinesis
Data Firehose
Amazon Redshift
Amazon ES
1
12
2
Amazon EC2
Spot Fleet
Amazon SNS CloudWatch Amazon EC2 Auto Scaling
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Evolution of big data at NuData (part 4)
AWS Cloud
Data processing workflow
Data operations monitoring
Amazon SNS CloudWatch
Amazon S3
Amazon Redshift
Kinesis
Data Firehose
Amazon ES
Amazon Athena
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Understated benefits of the cloud
Minor changes in architecture can have large impacts
Everyone talks about security, elasticity, and paying for usage
Shift away from do-it-yourself on Amazon EC2 to free up time to
innovate
Every decision made has a feedback loop: the underlying AWS bill!
Achieving innovation velocity requires focus
Delegate undifferentiated heavy lifting to managed services
Provide educational programs and reward innovations
Enable teams to drive business value through culture
S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Practical implementation caveats
Meet your new friend: AWS CloudFormation
There are alternatives—pick your poison!
Integrate with AWS Service Catalog
Provide guardrails as needed
Collaborate and partner
DevOps, SysOps, security, many specialized skill sets
Focus on compliance requirements
Understand relevant regulations
Key principle
If you made the model, you should own it (end to end)
AWS CloudFormation
AWS Service Catalog
AWS Organizations
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Powered by
machine learning
Online application origination
Growing issue as breaches expose more data
Uses synthetic identities to create accounts—or
sign up for credit cards online
How do you defend against synthetic identities?
Model development
We reduced model development time by 60
percent—the more we practice it, the better we
get!
Used a variety of AWS services
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Develop common libraries
AWS Cloud
Machine learning development library workflow
Data operations monitoring
AWS Cloud9 AWS CodeCommit
AWS CodeBuild
AWS CodePipeline Amazon S3
AWS CodeBuild
AWS Service Catalog AWS CloudTrailAWS Config CloudWatchAWS CloudFormation
1 2 3 4 5
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Prepare a dataset
AWS Cloud
VPC
Amazon SageMaker
Dataset preparation workflow
Data operations monitoring
CloudTrailAWS Config CloudWatch
1 2 3
Amazon Redshift Amazon Simple Storage
Service (S3)
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Train a model
AWS Cloud
Amazon S3
Data operations monitoring
Amazon SNS Amazon CloudWatch
SageMakerLambdaAWS Step Functions
Model training workflow
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Host a model
AWS Cloud
Amazon SNS
LambdaAmazon API Gateway
Amazon CloudWatch
SageMakerDynamoDB
Real-time machine learning API
Data operations monitoring
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Sample code
@RestController
public class ExampleHandler {
private String modelName = "exampleModel";
private Model model;
private Parameters parameters;
private SageMaker service;
@Autowired
public ExampleHandler(SageMaker service, Model model, Parameters parameters)
this.model = model;
this.modelParameters = modelParameters;
this.sageMakerService = sageMakerService;
}
@PostMapping("/predictions")
public Mono<ServerResponse> predict(Counter counter) {
parameters.setParameter("velocity", counter.getVelocity());
model.setModelName(this.modelName);
return Mono.fromFuture(service.invokeAsync(model, parameters));
}
}
S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Next steps, directions
Evolution is key to long-term success
Need to be able to respond rapidly to new threat vectors
Need to be able to innovate rapidly with new technologies
Goal is to protect every device and every transaction online
Cloud is key, but how you use it matters
No silver-bullet solution, not off the shelf
Focus on core business, offload undifferentiated heavy lifting
Open the discussion, keep innovating
AWS Solution: Fraud Detection Using Machine Learning
Mastercard: Brighterion, Ethoca, NuData Security
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Interested in NuDetect?
Mastercard is hiring!
Apply now at https://nudatasecurity.com/company/careers/
Join the conversation!
Follow us on Twitter: @NuDataSecurity
Follow us on LinkedIn: https://www.linkedin.com/company/nudata-security/
Looking to reduce consumer friction?
Contact a sales engineer at sales@nudatasecurity.com
Take a peek at our demos: https://nudatasecurity.com/solutions/demo/
Lots of options for preventing fraud:
NuDetect, ATO Protect, Smart Interface, Trusted Device
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T
Thank you!
S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Christopher Marsh-Bourdon
Principle Solutions Architect
Amazon Web Services
Justin Fox
Head of Platform
NuData Security

More Related Content

What's hot

What's hot (20)

Building ML platforms in Financial Services with serverless technology - FSV2...
Building ML platforms in Financial Services with serverless technology - FSV2...Building ML platforms in Financial Services with serverless technology - FSV2...
Building ML platforms in Financial Services with serverless technology - FSV2...
 
Migrating Business Critical Applications to AWS
Migrating Business Critical Applications to AWSMigrating Business Critical Applications to AWS
Migrating Business Critical Applications to AWS
 
Build a Next-Gen Meeting Room Experience Using Alexa for Business - SVC203 - ...
Build a Next-Gen Meeting Room Experience Using Alexa for Business - SVC203 - ...Build a Next-Gen Meeting Room Experience Using Alexa for Business - SVC203 - ...
Build a Next-Gen Meeting Room Experience Using Alexa for Business - SVC203 - ...
 
What's New with Amazon S3, Amazon EFS, and Other AWS Storage Services - STG20...
What's New with Amazon S3, Amazon EFS, and Other AWS Storage Services - STG20...What's New with Amazon S3, Amazon EFS, and Other AWS Storage Services - STG20...
What's New with Amazon S3, Amazon EFS, and Other AWS Storage Services - STG20...
 
Performing real-time ETL into data lakes - ADB202 - Santa Clara AWS Summit.pdf
Performing real-time ETL into data lakes - ADB202 - Santa Clara AWS Summit.pdfPerforming real-time ETL into data lakes - ADB202 - Santa Clara AWS Summit.pdf
Performing real-time ETL into data lakes - ADB202 - Santa Clara AWS Summit.pdf
 
Threat detection and mitigation at AWS - SEC301 - Santa Clara AWS Summit
Threat detection and mitigation at AWS - SEC301 - Santa Clara AWS SummitThreat detection and mitigation at AWS - SEC301 - Santa Clara AWS Summit
Threat detection and mitigation at AWS - SEC301 - Santa Clara AWS Summit
 
What’s new with Amazon S3, Amazon EFS, and other AWS storage services - STG20...
What’s new with Amazon S3, Amazon EFS, and other AWS storage services - STG20...What’s new with Amazon S3, Amazon EFS, and other AWS storage services - STG20...
What’s new with Amazon S3, Amazon EFS, and other AWS storage services - STG20...
 
Introduction to EC2 A1 instances, powered by the AWS Graviton processor - CMP...
Introduction to EC2 A1 instances, powered by the AWS Graviton processor - CMP...Introduction to EC2 A1 instances, powered by the AWS Graviton processor - CMP...
Introduction to EC2 A1 instances, powered by the AWS Graviton processor - CMP...
 
Databases on AWS - The right tool for the right job - ADB203 - Santa Clara AW...
Databases on AWS - The right tool for the right job - ADB203 - Santa Clara AW...Databases on AWS - The right tool for the right job - ADB203 - Santa Clara AW...
Databases on AWS - The right tool for the right job - ADB203 - Santa Clara AW...
 
Move users to AWS with Amazon WorkSpaces and Amazon AppStream 2-0
Move users to AWS with Amazon WorkSpaces and Amazon AppStream 2-0Move users to AWS with Amazon WorkSpaces and Amazon AppStream 2-0
Move users to AWS with Amazon WorkSpaces and Amazon AppStream 2-0
 
Deploy and scale your first cloud application with Amazon Lightsail - CMP208 ...
Deploy and scale your first cloud application with Amazon Lightsail - CMP208 ...Deploy and scale your first cloud application with Amazon Lightsail - CMP208 ...
Deploy and scale your first cloud application with Amazon Lightsail - CMP208 ...
 
Connecting your devices at scale, ft. Discovery - SVC205 - New York AWS Summit
Connecting your devices at scale, ft. Discovery - SVC205 - New York AWS SummitConnecting your devices at scale, ft. Discovery - SVC205 - New York AWS Summit
Connecting your devices at scale, ft. Discovery - SVC205 - New York AWS Summit
 
Network visibility into the traffic traversing your AWS infrastructure - SVC2...
Network visibility into the traffic traversing your AWS infrastructure - SVC2...Network visibility into the traffic traversing your AWS infrastructure - SVC2...
Network visibility into the traffic traversing your AWS infrastructure - SVC2...
 
Everything You Need to Know About Big Data: From Architectural Principles to ...
Everything You Need to Know About Big Data: From Architectural Principles to ...Everything You Need to Know About Big Data: From Architectural Principles to ...
Everything You Need to Know About Big Data: From Architectural Principles to ...
 
What's new in Amazon Aurora - ADB204 - Santa Clara AWS Summit.pdf
What's new in Amazon Aurora - ADB204 - Santa Clara AWS Summit.pdfWhat's new in Amazon Aurora - ADB204 - Santa Clara AWS Summit.pdf
What's new in Amazon Aurora - ADB204 - Santa Clara AWS Summit.pdf
 
Twelve-factor serverless applications - MAD302 - Santa Clara AWS Summit
Twelve-factor serverless applications - MAD302 - Santa Clara AWS SummitTwelve-factor serverless applications - MAD302 - Santa Clara AWS Summit
Twelve-factor serverless applications - MAD302 - Santa Clara AWS Summit
 
Threat Detection using artificial intelligence
Threat Detection using artificial intelligenceThreat Detection using artificial intelligence
Threat Detection using artificial intelligence
 
Next generation intelligent data lakes, powered by GraphQL & AWS AppSync - MA...
Next generation intelligent data lakes, powered by GraphQL & AWS AppSync - MA...Next generation intelligent data lakes, powered by GraphQL & AWS AppSync - MA...
Next generation intelligent data lakes, powered by GraphQL & AWS AppSync - MA...
 
Introducing AWS App Mesh - MAD303 - Santa Clara AWS Summit
Introducing AWS App Mesh - MAD303 - Santa Clara AWS SummitIntroducing AWS App Mesh - MAD303 - Santa Clara AWS Summit
Introducing AWS App Mesh - MAD303 - Santa Clara AWS Summit
 
Building IoT applications for a connected home - SVC206 - Santa Clara AWS Summit
Building IoT applications for a connected home - SVC206 - Santa Clara AWS SummitBuilding IoT applications for a connected home - SVC206 - Santa Clara AWS Summit
Building IoT applications for a connected home - SVC206 - Santa Clara AWS Summit
 

Similar to Using ML to detect and prevent fraud without compromising user experience - FSV302 - New York AWS Summit

機器學習技術在工業應用上的最佳實務
機器學習技術在工業應用上的最佳實務機器學習技術在工業應用上的最佳實務
機器學習技術在工業應用上的最佳實務
Amazon Web Services
 

Similar to Using ML to detect and prevent fraud without compromising user experience - FSV302 - New York AWS Summit (20)

A culture of rapid innovation with DevOps, microservices, & serverless - MAD2...
A culture of rapid innovation with DevOps, microservices, & serverless - MAD2...A culture of rapid innovation with DevOps, microservices, & serverless - MAD2...
A culture of rapid innovation with DevOps, microservices, & serverless - MAD2...
 
Machine learning at the edge for industrial applications - SVC302 - New York ...
Machine learning at the edge for industrial applications - SVC302 - New York ...Machine learning at the edge for industrial applications - SVC302 - New York ...
Machine learning at the edge for industrial applications - SVC302 - New York ...
 
AWS Summit Singapore 2019 | AWS Techfest Opening Keynote
AWS Summit Singapore 2019 | AWS Techfest Opening KeynoteAWS Summit Singapore 2019 | AWS Techfest Opening Keynote
AWS Summit Singapore 2019 | AWS Techfest Opening Keynote
 
How to speed up and scale your innovation efforts - MAD203 - Chicago AWS Summit
How to speed up and scale your innovation efforts - MAD203 - Chicago AWS SummitHow to speed up and scale your innovation efforts - MAD203 - Chicago AWS Summit
How to speed up and scale your innovation efforts - MAD203 - Chicago AWS Summit
 
Architetture per l'analisi di flussi di dati in tempo reale
Architetture per l'analisi di flussi di dati in tempo realeArchitetture per l'analisi di flussi di dati in tempo reale
Architetture per l'analisi di flussi di dati in tempo reale
 
Threat detection and mitigation at AWS
Threat detection and mitigation at AWSThreat detection and mitigation at AWS
Threat detection and mitigation at AWS
 
Threat detection and mitigation at AWS - SEC201 - New York AWS Summit
Threat detection and mitigation at AWS - SEC201 - New York AWS SummitThreat detection and mitigation at AWS - SEC201 - New York AWS Summit
Threat detection and mitigation at AWS - SEC201 - New York AWS Summit
 
Building Data Lakes for Analytics on AWS - ADB201 - Anaheim AWS Summit
Building Data Lakes for Analytics on AWS - ADB201 - Anaheim AWS SummitBuilding Data Lakes for Analytics on AWS - ADB201 - Anaheim AWS Summit
Building Data Lakes for Analytics on AWS - ADB201 - Anaheim AWS Summit
 
Sicurezza in AWS automazione e best practice
Sicurezza in AWS automazione e best practiceSicurezza in AWS automazione e best practice
Sicurezza in AWS automazione e best practice
 
How Millennium Management achieves provable security with AWS Zelkova - FSV30...
How Millennium Management achieves provable security with AWS Zelkova - FSV30...How Millennium Management achieves provable security with AWS Zelkova - FSV30...
How Millennium Management achieves provable security with AWS Zelkova - FSV30...
 
利用AWS打造一站式旅遊服務平台
利用AWS打造一站式旅遊服務平台利用AWS打造一站式旅遊服務平台
利用AWS打造一站式旅遊服務平台
 
A Culture of Rapid Innovation with DevOps, Microservices, & Serverless - MAD2...
A Culture of Rapid Innovation with DevOps, Microservices, & Serverless - MAD2...A Culture of Rapid Innovation with DevOps, Microservices, & Serverless - MAD2...
A Culture of Rapid Innovation with DevOps, Microservices, & Serverless - MAD2...
 
Detecting and mitigating threats with AWS - SEC301 - Chicago AWS Summit
Detecting and mitigating threats with AWS - SEC301 - Chicago AWS SummitDetecting and mitigating threats with AWS - SEC301 - Chicago AWS Summit
Detecting and mitigating threats with AWS - SEC301 - Chicago AWS Summit
 
The Power of Perspective
The Power of PerspectiveThe Power of Perspective
The Power of Perspective
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWS
 
Find all the threats: AWS threat detection and mitigation - SEC302 - Santa Cl...
Find all the threats: AWS threat detection and mitigation - SEC302 - Santa Cl...Find all the threats: AWS threat detection and mitigation - SEC302 - Santa Cl...
Find all the threats: AWS threat detection and mitigation - SEC302 - Santa Cl...
 
Getting Started with Microservices, Containers, and Serverless Architectures
Getting Started with Microservices, Containers, and Serverless ArchitecturesGetting Started with Microservices, Containers, and Serverless Architectures
Getting Started with Microservices, Containers, and Serverless Architectures
 
AWS Cloud Adoption and the Future of Financial Services
AWS Cloud Adoption and the Future of Financial ServicesAWS Cloud Adoption and the Future of Financial Services
AWS Cloud Adoption and the Future of Financial Services
 
機器學習技術在工業應用上的最佳實務
機器學習技術在工業應用上的最佳實務機器學習技術在工業應用上的最佳實務
機器學習技術在工業應用上的最佳實務
 
Build data-drive, high performance, internet scale applications with AWS Data...
Build data-drive, high performance, internet scale applications with AWS Data...Build data-drive, high performance, internet scale applications with AWS Data...
Build data-drive, high performance, internet scale applications with AWS Data...
 

More from Amazon Web Services

Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWS
Amazon Web Services
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch Deck
Amazon Web Services
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without servers
Amazon Web Services
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
Amazon Web Services
 

More from Amazon Web Services (20)

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS Fargate
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWS
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot
 
Open banking as a service
Open banking as a serviceOpen banking as a service
Open banking as a service
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
 
Computer Vision con AWS
Computer Vision con AWSComputer Vision con AWS
Computer Vision con AWS
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatare
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e web
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWS
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch Deck
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without servers
 
Fundraising Essentials
Fundraising EssentialsFundraising Essentials
Fundraising Essentials
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
 

Using ML to detect and prevent fraud without compromising user experience - FSV302 - New York AWS Summit

  • 1. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Using ML to detect and prevent fraud without compromising user experience Christopher Marsh-Bourdon Principle Solutions Architect Amazon Web Services F S V 3 0 2 Justin Fox Head of Platform Innovation NuData Security
  • 2. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Agenda What is NuDetect? Layers of threat intelligence Big-data processing Let’s talk DataOps Next steps
  • 3. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Related breakouts AIM304 – Machine learning for developers & data scientists with Amazon SageMaker Cyrus Vahid, AWS AIM306 – Fraud detection using machine learning with Amazon SageMaker Cyrus Vahid, AWS AIM309 – Setting up custom machine learning environments on AWS Shashank Prasanna, AWS
  • 4. S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 5. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Let’s start with our history NuData Security was born in the AWS Cloud • Early adopters in 2007, on Amazon EC2 Classic • As the cloud innovated we leveraged the advances • VPC? Check. Config? Check. Lambda? Check. Targeted identity verification to reduce fraud • E-Commerce, Financial Institutions • Focus on consumer experience, #frictionless • Powered by machine learning
  • 6. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T What does the landscape look like? of payment executives at FIs believe that the evolution of digital as a channel adds significant risk of fraud180% of credit losses and 5 percent of charged-off accounts are due to credit application fraud using synthetic identities3 Cybercrime is more sophisticated than ever and the costs are mounting As banking moves toward a more digital experience with increased points of interaction, it is more critical than ever to accurately identify your real customers from fraudulent attempts to manage risk 1/3 of US businesses have had customer data breached2 cost of cybercrime to US issuers by 20194 $2 trillion 20% 1. LexisNexis, "True Cost of Fraud,” 2017 2. Javelin 2017 State of Authentication Report 3. Auriemma Consulting Group, "Synthetic Identity Fraud Cost Lenders $6 Billion In 2016," August 2017 4. Forbes, “Cyber crime costs projected to reach $2 trillion by 2019," 2016
  • 7. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Why do we care? Accurate authentication is critical, but it requires careful balancing of security needs with a great user experience #1 Identity verification is among the top three challenges facing financial institutions1 36% increase in incidence of account takeover since 2015 and a 60 percent increase in losses2 74% of financial institutions state that improving the consumer experience is an important component in a business case for a new fraud solution3
  • 8. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T We combine layers of security Device, connection, and location identification Trust that the real consumer is using the device. Behavioral analytics Continuously verify the consumer. Trust the behavior. Passive (invisible) biometric verification Trust the consumer based on natural behaviors and sensory inputs. Real-time trust consortium Aggregated, network-level data from all behavioral interactions. Trust the consortium.
  • 9. S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 10. S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 11. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Intro to our architecture Systems evolve Monolith Microservices Containers Functions Leverage managed services Lower operational overhead Acts as an interface between systems Key principles Creating a DevOps culture, teams own stuff You made the model, you own it (end to end)
  • 12. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T NuDetect architecture Corporate data center AWS Cloud Amazon CloudFront AWS PrivateLinkAmazon VPC AWS Cloud AWS Global Accelerator Elastic Load Balancing Amazon EC2 AWS Lambda Amazon ECS Connectivity options Real-time scoring engine
  • 13. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Microservice architecture AWS Cloud Real-time device intelligence Real-time passive biometrics Real-time trust consortium Amazon DynamoDB Amazon RDS Amazon ElastiCache Amazon API Gateway Elastic Load Balancing Elastic Load Balancing Amazon EC2 Lambda Amazon ECS
  • 14. S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 15. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T How much data do you need? Big data is just another word for data hoarder Every service generates data Telemetry data/metrics System logging Application logging Performance data Let’s be real: More data equals more problems Compliance Regulations Privacy
  • 16. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Evolution of big data at NuData (part 1) Data operations monitoring Elastic Load Balancing Amazon EC2 ElastiCache Amazon S3 Amazon Redshift 1 12 2 Amazon EC2 Spot Fleet Amazon SNS Amazon CloudWatch Amazon EC2 Auto Scaling AWS Cloud Data processing workflow Cassandra
  • 17. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Evolution of big data at NuData (part 2) Event aggregation workflow Data operations monitoring ElastiCache Amazon EC2 Elastic Load Balancing Amazon EC2 ElastiCache Amazon S3 Amazon Redshift 1 12 2 Amazon EC2 Spot Fleet Amazon SNS CloudWatch Amazon EC2 Auto Scaling AWS Cloud Data processing workflow Cassandra
  • 18. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Evolution of big data at NuData (part 3) AWS Cloud Event aggregation workflow Data operations monitoring Data processing workflow ElastiCache Amazon EC2 Elastic Load Balancing Amazon EC2 ElastiCache Amazon S3 Amazon Kinesis Data Firehose Amazon Redshift Amazon ES 1 12 2 Amazon EC2 Spot Fleet Amazon SNS CloudWatch Amazon EC2 Auto Scaling
  • 19. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Evolution of big data at NuData (part 4) AWS Cloud Data processing workflow Data operations monitoring Amazon SNS CloudWatch Amazon S3 Amazon Redshift Kinesis Data Firehose Amazon ES Amazon Athena
  • 20. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Understated benefits of the cloud Minor changes in architecture can have large impacts Everyone talks about security, elasticity, and paying for usage Shift away from do-it-yourself on Amazon EC2 to free up time to innovate Every decision made has a feedback loop: the underlying AWS bill! Achieving innovation velocity requires focus Delegate undifferentiated heavy lifting to managed services Provide educational programs and reward innovations Enable teams to drive business value through culture
  • 21. S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 22. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Practical implementation caveats Meet your new friend: AWS CloudFormation There are alternatives—pick your poison! Integrate with AWS Service Catalog Provide guardrails as needed Collaborate and partner DevOps, SysOps, security, many specialized skill sets Focus on compliance requirements Understand relevant regulations Key principle If you made the model, you should own it (end to end) AWS CloudFormation AWS Service Catalog AWS Organizations
  • 23. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Powered by machine learning Online application origination Growing issue as breaches expose more data Uses synthetic identities to create accounts—or sign up for credit cards online How do you defend against synthetic identities? Model development We reduced model development time by 60 percent—the more we practice it, the better we get! Used a variety of AWS services
  • 24. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Develop common libraries AWS Cloud Machine learning development library workflow Data operations monitoring AWS Cloud9 AWS CodeCommit AWS CodeBuild AWS CodePipeline Amazon S3 AWS CodeBuild AWS Service Catalog AWS CloudTrailAWS Config CloudWatchAWS CloudFormation 1 2 3 4 5
  • 25. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Prepare a dataset AWS Cloud VPC Amazon SageMaker Dataset preparation workflow Data operations monitoring CloudTrailAWS Config CloudWatch 1 2 3 Amazon Redshift Amazon Simple Storage Service (S3)
  • 26. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Train a model AWS Cloud Amazon S3 Data operations monitoring Amazon SNS Amazon CloudWatch SageMakerLambdaAWS Step Functions Model training workflow
  • 27. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Host a model AWS Cloud Amazon SNS LambdaAmazon API Gateway Amazon CloudWatch SageMakerDynamoDB Real-time machine learning API Data operations monitoring
  • 28. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Sample code @RestController public class ExampleHandler { private String modelName = "exampleModel"; private Model model; private Parameters parameters; private SageMaker service; @Autowired public ExampleHandler(SageMaker service, Model model, Parameters parameters) this.model = model; this.modelParameters = modelParameters; this.sageMakerService = sageMakerService; } @PostMapping("/predictions") public Mono<ServerResponse> predict(Counter counter) { parameters.setParameter("velocity", counter.getVelocity()); model.setModelName(this.modelName); return Mono.fromFuture(service.invokeAsync(model, parameters)); } }
  • 29. S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 30. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Next steps, directions Evolution is key to long-term success Need to be able to respond rapidly to new threat vectors Need to be able to innovate rapidly with new technologies Goal is to protect every device and every transaction online Cloud is key, but how you use it matters No silver-bullet solution, not off the shelf Focus on core business, offload undifferentiated heavy lifting Open the discussion, keep innovating AWS Solution: Fraud Detection Using Machine Learning Mastercard: Brighterion, Ethoca, NuData Security
  • 31. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Interested in NuDetect? Mastercard is hiring! Apply now at https://nudatasecurity.com/company/careers/ Join the conversation! Follow us on Twitter: @NuDataSecurity Follow us on LinkedIn: https://www.linkedin.com/company/nudata-security/ Looking to reduce consumer friction? Contact a sales engineer at sales@nudatasecurity.com Take a peek at our demos: https://nudatasecurity.com/solutions/demo/ Lots of options for preventing fraud: NuDetect, ATO Protect, Smart Interface, Trusted Device
  • 32. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Thank you! S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved. Christopher Marsh-Bourdon Principle Solutions Architect Amazon Web Services Justin Fox Head of Platform NuData Security