Financial services companies are using machine learning to reduce fraud, streamline processes, and improve their bottom line. AWS provides tools that help them easily use AI tools like MXNet and Tensor Flow to perform predictive analytics, clustering, and more advanced data analyses. In this session, hear how IHS Markit has used machine learning on AWS to help global banking institutions manage their commodities portfolios. Learn how Amazon Machine Learning can take the hassle out of AI.

1. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
AWS re:INVENT
Machine Learning in Capital Markets
F r a n k T a r s i l l o , I H S M a r k i t
P e t e r W i l l i a m s , A W S F i n a n c i a l S e r v i c e s
N o v e m b e r 2 8 , 2 0 1 7

2. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Takeaways from today’s session
1. How is machine learning changing financial services?
2. Case study: IHS Markit’s commodity inventory solution
3. How do customers get started?
4. Best practices when building machine learning in the cloud

3. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
How is machine learning
changing financial services?

4. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Artificial intelligence
A system or service
that can perform
tasks that usually
require
human intelligence
AA
Hardware + learning
algorithms
Fit a network structure
to the data
Fit a function
to the data
AI
ML
DL

5. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
T h e c h a l l e n g e :
Scale
Data Training Prediction
PBs and EBs of
existing data
Aggressive migration
Tons of GPUs
Elastic capacity
Pre-built images
Tons of GPUs and CPUs
Serverless
At the edge,
on IoT devices

6. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Business group Use case ML models AWS tools
Asset management
Equity ratings
Portfolio management
Portfolio optimization
Machine learning
(clustering, SVM,
logistic regression,
Gaussian processes)
Deep learning (embedding,
matrix factorization, LSTM,
conversational UI)
Graphical models
Amazon Machine Learning
Deep Learning MXNet
SparkML on Amazon EMR
TensorFlow
Banking
Credit card/lending fraud
Customer onboarding
Digital banking
Compliance
Anti-money laundering,
Counter-terrorism financing
Due diligence
Security
Cyber-attack detection
Data leak detection
Virus detection
Financial services use cases

7. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
AWS has become the center of gravity for AI

8. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Case study

9. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Commodity inventory challenges
Global warehouses are all different
Diverse flow of paper documents, from warehouse
inventory reports to bills of lading
Digitize, classify, and aggregate the document flow
Improve cost and risk management
Localization diversity
Eliminate error-prone manual operations

10. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Singapore Al 123.4 mT
Vlissingen Al 234.5 mT
Qingdao Al 567.8 mT
Vendors
Report generation
Vendors continue to generate their
reports as usual. Documents are
redirected to a Markit server.
Process
Markit scrapes the critical data
from the warehouse’s unique
report using a variety of
technologies, including OCR.
Audit
Markit stores a digital copy of
the original document for
auditing purposes.
Disseminate
The data is standardized for
language and terminology,
then compiled onto a
customer portal.
IHS Markit Trading firms
Data access
Dependent teams at the
trading firms connect to the
portal to pull a personalized
view of the required data.
Logistics teams
Finance teams
Compliance teams
Schedulers/traders
Commodity inventory solution
Singapore
Vlissingen
青岛

11. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
IHSM Product VPC IHSM Commodity Tracker IHSM Product VPC
IHS Markit—cloud strategy
Cloud-first strategy
Cloud native vs. lift and shift
Time-to-market focus
Investment upfront
Refreshing the estate
Financial transparency
A DevOps world
Global scale
Cost-savings in the end
Global
Physical network
IHSM datacenter(s)
Oracle SAN
Existing IHSM product deployments
Customer datacenter
Services End user
Services Encryption
S3 SES
Services Encryption Services Encryption
RDS SESDynamicDB
Shared services with scale (Iaas/SaaS/PaaS)
Cloud
enhancement
Cloud
enhancement

12. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Architecture approach
Microservices design approach
PaaS supporting orchestration and discovery
OCR, classification, and analysis documents
Cloud enablement with some lock-in
API-driven
Modern UI, SSO, preferences, notifications
SDLC-Agile, CI/CD, high velocity of change
Highly available (multi-AZ/global)

13. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Machine learning enablement
Document classification and templates to reduce exceptions
Configuration data and models (Keras + TensorFlow)
Use of AML-based images to tool vs. DIY
AWS compute with GPU on-demand for trainer
Data lake of document classifications (strategic)
OCR
Classification
predictor
QA reviewMLDoc APIs
Document
repository
Classification
trainer
Corrected
predictions

14. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
ML product maintenance
P2 instances
ML AMI
ML AMI
Production predictor
(AWS Lambda)
Job scheduler
Train model
with new data
Design
new model
New
document
Prediction
corrections
Trained
models
Documents Results
Data lake (Amazon S3)

15. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Result

16. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
80%
of docs STP
Focus human effort
on the exceptions
60%
improvement
in timeliness
Reduce risk by cutting
the lag between data
collection and use
50%
increase in
efficiency
Empower teams
to focus energy on
value-creation activities
Commodity tracker benefits

17. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Getting started with ML

18. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Machine Learning (Amazon ML)
Easy-to-use, managed machine
learning service built for developers
Robust, powerful machine-learning technology
based on Amazon’s internal systems
Create models using your data that is
already stored in the AWS cloud
Deploy models to production in seconds

19. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Easy to use and developer-friendly
Use the intuitive, powerful service console to
build and explore your initial models
Data retrieval
Model training, quality evaluation, fine-tuning
Deployment and management
Automate model lifecycle with
fully featured APIs and SDKs
Java, Python, .NET, JavaScript, Ruby, PHP
Easily create smart iOS and Android
applications with AWS Mobile SDK

20. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Powerful machine learning technology
Based on Amazon’s battle-hardened
internal systems
Not just the algorithms
Smart data transformations
Input data and model quality alerts
Built-in industry best practices
Grows with your needs
Train on up to 100 GB of data
Generate billions of predictions
Obtain predictions in batches or real time

21. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Integrated with the AWS data ecosystem
Access data that is stored in Amazon S3, Amazon
Redshift, or MySQL databases in Amazon RDS
Output predictions to Amazon S3 for easy
integration with your data flows
Use AWS Identity and Access Management (IAM)
for fine-grained data access permission policies

22. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Fully managed model
and prediction services
End-to-end service with no servers
to provision and manage
One-click production model deployment
Programmatically query model metadata
to enable automatic retraining workflows
Monitor prediction usage patterns
with Amazon CloudWatch metrics

23. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Three supported types of predictions
Binary classification
Predict the answer to a yes/no question
Multiclass classification
Predict the correct category from a list
Regression
Predict the value of a numeric variable

24. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Infrastructure
Frameworks
Platforms Amazon ML ECSSpark & EMR Kinesis Batch
GPU MobileCPU IoT
Services
Amazon Lex
(language)
Amazon Polly
(speech)
Amazon Rekognition
(vision)
Apache
MXNet
Torch
Cognitive
toolkit
KerasTheano
Caffe2
& Caffe
Tensor
Flow
AWS Deep Learning AMI
Gluon
A W S A I :
Democratized artificial intelligence

25. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Key takeaways

26. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Key takeaways
AWS machine-learning services can help transform your applications and
improve your bottom line
Get started today:
- Try the AML tutorial at https://aws.amazon.com/aml/getting-started/

27. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Please remember to rate this
session in the mobile app

28. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Thank you!
F r a n k T a r s i l l o , f r a n k . t a r s i l l o @ i h s m a r k i t . c o m
P e t e r W i l l i a m s , w i l l p e @ a m a z o n . c o m
P l e a s e f i l l o u t a s u r v e y o f t h i s s e s s i o n : G P S T E C 3 0 5