Amazon Machine Learning (Amazon ML) is a service that makes it easy for developers of all skill levels to use machine learning technology. Amazon Machine Learning’s powerful algorithms create machine learning models by finding patterns in your existing data. The service uses these models to process new data and generate predictions for your application. In this session, we will show you how to use machine learning with the data you already have to arrive at accurate and actionable predictions - to create smart applications. You will learn how to use and integrate Amazon ML into your applications to take advantage of predictive analysis in the cloud.

1. © 2016, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Guy Ernest, Business Development Manager Machine Learning, AWS
July 2016
Getting Started with
Amazon Machine Learning

2. Agenda
Machine learning and the data ecosystem
Smart applications by example (and counter example)
Amazon Machine Learning features and benefits
Building a model demo
Q&A

3. Three types of data-driven development
Retrospective
analysis and
reporting
Amazon Redshift
Amazon RDS
Amazon S3
Amazon EMR

4. Three types of data-driven development
Retrospective
analysis and
reporting
Here-and-now
real-time processing
and dashboards
Amazon Kinesis
Amazon EC2
AWS Lambda
Amazon Redshift,
Amazon RDS
Amazon S3
Amazon EMR

5. Three types of data-driven development
Retrospective
analysis and
reporting
Here and now
real-time processing
and dashboards
Predictions
to enable smart
applications
Amazon Kinesis
Amazon EC2
AWS Lambda
Amazon Redshift
Amazon RDS
Amazon S3
Amazon EMR

6. Machine learning and smart applications
Machine learning is the technology that
automatically finds patterns in your data and
uses them to make predictions for new data
points as they become available

7. Machine learning and smart applications
Machine learning is the technology that
automatically finds patterns in your data and
uses them to make predictions for new data
points as they become available
Your data + machine learning = smart applications

8. Smart applications by example
Based on what you
know about the user:
Will they use your
product?

9. Smart applications by example
Based on what you
know about the user:
Will they use your
product?
Based on what you
know about an order:
Is this order
fraudulent?

10. Smart applications by example
Based on what you
know about the user:
Will they use your
product?
Based on what you
know about an order:
Is this order
fraudulent?
Based on what you know
about a news article:
What other articles are
interesting?

11. And a few more examples…
Fraud detection Detecting fraudulent transactions, filtering spam emails,
flagging suspicious reviews, …
Personalization Recommending content, predictive content loading,
improving user experience, …
Targeted marketing Matching customers and offers, choosing marketing
campaigns, cross-selling and up-selling, …
Content classification Categorizing documents, matching hiring managers and
resumes, …
Churn prediction Finding customers who are likely to stop using the
service, upgrade targeting, …
Customer support Predictive routing of customer emails, social media
listening, …

12. Building smart applications – a counter pattern
Dear Guy,
This awesome quadcopter is on sale
for just $49.99!

13. Smart applications by counter example
SELECT c.ID
FROM customers c
LEFT JOIN orders o
ON c.ID = o.customer
GROUP BY c.ID
HAVING o.date > GETDATE() – 30
We can start by sending
the offer to all customers
who placed an order in
the last 30 days

14. Smart applications by counter example
SELECT c.ID
FROM customers c
LEFT JOIN orders o
ON c.ID = o.customer
GROUP BY c.ID
HAVING O.CATEGORY = ‘TOYS’
AND o.date > GETDATE() – 30
… let’s narrow it down to
just customers who
bought toys

15. Smart applications by counter example
SELECT c.ID
FROM customers c
LEFT JOIN orders o
ON c.ID = o.customer
LEFT JOIN PRODUCTS P
ON P.ID = O.PRODUCT
GROUP BY c.ID
HAVING o.category = ‘toys’
AND ((P.DESCRIPTION LIKE ‘%HELICOPTER%’
AND O.DATE > GETDATE() - 60)
OR (COUNT(*) > 2
AND SUM(o.price) > 200
AND o.date > GETDATE() – 30)
)
… and expand the query
to customers who
purchased other toy
helicopters recently

16. Smart applications by counter example
SELECT c.ID
FROM customers c
LEFT JOIN orders o
ON c.ID = o.customer
LEFT JOIN products p
ON p.ID = o.product
GROUP BY c.ID
HAVING o.category = ‘toys’
AND ((p.description LIKE ‘%COPTER%’
AND o.date > GETDATE() - 60)
OR (COUNT(*) > 2
AND SUM(o.price) > 200
AND o.date > GETDATE() – 30)
)
… but what about
quadcopters?

17. Smart applications by counter example
SELECT c.ID
FROM customers c
LEFT JOIN orders o
ON c.ID = o.customer
LEFT JOIN products p
ON p.ID = o.product
GROUP BY c.ID
HAVING o.category = ‘toys’
AND ((p.description LIKE ‘%copter%’
AND o.date > GETDATE() - 120)
OR (COUNT(*) > 2
AND SUM(o.price) > 200
AND o.date > GETDATE() – 30)
)
… maybe we should go
back further in time

18. Smart applications by counter example
SELECT c.ID
FROM customers c
LEFT JOIN orders o
ON c.ID = o.customer
LEFT JOIN products p
ON p.ID = o.product
GROUP BY c.ID
HAVING o.category = ‘toys’
AND ((p.description LIKE ‘%copter%’
AND o.date > GETDATE() - 120)
OR (COUNT(*) > 2
AND SUM(o.price) > 200
AND o.date > GETDATE() – 40)
)
… tweak the query more

19. Smart applications by counter example
SELECT c.ID
FROM customers c
LEFT JOIN orders o
ON c.ID = o.customer
LEFT JOIN products p
ON p.ID = o.product
GROUP BY c.ID
HAVING o.category = ‘toys’
AND ((p.description LIKE ‘%copter%’
AND o.date > GETDATE() - 120)
OR (COUNT(*) > 2
AND SUM(o.price) > 150
AND o.date > GETDATE() – 40)
)
… again

20. Smart applications by counter example
SELECT c.ID
FROM customers c
LEFT JOIN orders o
ON c.ID = o.customer
LEFT JOIN products p
ON p.ID = o.product
GROUP BY c.ID
HAVING o.category = ‘toys’
AND ((p.description LIKE ‘%copter%’
AND o.date > GETDATE() - 90)
OR (COUNT(*) > 2
AND SUM(o.price) > 150
AND o.date > GETDATE() – 40)
)
… and again

21. Smart applications by counter example
SELECT c.ID
FROM customers c
LEFT JOIN orders o
ON c.ID = o.customer
LEFT JOIN products p
ON p.ID = o.product
GROUP BY c.ID
HAVING o.category = ‘toys’
AND ((p.description LIKE ‘%copter%’
AND o.date > GETDATE() - 90)
OR (COUNT(*) > 2
AND SUM(o.price) > 150
AND o.date > GETDATE() – 40)
)
Use machine learning
technology to learn your
business rules from data!

22. Why aren’t there more smart applications?
1. Machine learning expertise is rare.
2. Building and scaling machine learning technology is
hard.
3. Closing the gap between models and applications is
time-consuming and expensive.

23. Building smart applications today
Expertise Technology Operationalization
Limited supply of
data scientists
Many choices, few
mainstays
Complex and error-prone
data workflows
Expensive to hire
or outsource
Difficult to use and scale Custom platforms and
APIs
Many moving pieces lead
to custom solutions every
time
Reinventing the model
lifecycle management
wheel

24. What if there were a better
way?

25. Introducing Amazon Machine Learning
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 already
stored in the AWS Cloud
Deploy models to production in seconds

26. 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

27. 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 in real time

28. Integrated with AWS data ecosystem
Access data that is stored in Amazon S3,
Amazon Redshift, or MySQL databases in
Amazon RDS
Output predictions to S3 for easy integration
with your data flows
Use AWS Identity and Access Management
(IAM) for fine-grained data-access permission
policies

29. 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

30. Pay-as-you-go and inexpensive
Data analysis, model training, and
evaluation: $0.42/instance hour
Batch predictions: $0.10/1000
Real-time predictions: $0.10/1000
+ hourly capacity reservation charge

31. 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

32. Get started quickly
Create, access, and manage all
Amazon ML entities through the AWS
Management Console
Easily learn to build a model with the
provided tutorial and dataset
Add prediction capabilities to your iOS
and Android applications with the AWS
Mobile SDK
Use Amazon ML APIs, CLIs, or SDKs

33. Build
model
Evaluate and
optimize
Retrieve
predictions
1 2 3
Building smart applications with Amazon ML

34. Train
model
Evaluate and
optimize
Retrieve
predictions
1 2 3
Building smart applications with Amazon ML
- Create a datasource object pointing to your data
- Explore and understand your data
- Transform data and train your model

35. Create a datasource object
>>> import boto
>>> ml = boto.connect_machinelearning()
>>> ds = ml.create_data_source_from_s3(
data_source_id = ’my_datasource',
data_spec= {
'DataLocationS3':'s3://bucket/input/',
'DataSchemaLocationS3':'s3://bucket/input/.schema'},
compute_statistics = True)

36. Explore and understand your data

37. Train your model
>>> import boto
>>> ml = boto.connect_machinelearning()
>>> model = ml.create_ml_model(
ml_model_id=’my_model',
ml_model_type='REGRESSION',
training_data_source_id='my_datasource')

38. Train
model
Evaluate and
optimize
Retrieve
predictions
1 2 3
Building smart applications with Amazon ML
- Understand model quality
- Adjust model interpretation

39. Explore model quality

40. Fine-tune model interpretation

41. Fine-tune model interpretation

42. Train
model
Evaluate and
optimize
Retrieve
predictions
1 2 3
Building smart applications with Amazon ML
- Batch predictions
- Real-time predictions

43. Batch predictions
Asynchronous, large-volume prediction generation
Request through service console or API
Best for applications that deal with batches of data records
>>> import boto
>>> ml = boto.connect_machinelearning()
>>> model = ml.create_batch_prediction(
batch_prediction_id = 'my_batch_prediction’
batch_prediction_data_source_id = ’my_datasource’
ml_model_id = ’my_model',
output_uri = 's3://examplebucket/output/’)

44. Real-time predictions
Synchronous, low-latency, high-throughput prediction generation
Request through service API or server or mobile SDKs
Best for interaction applications that deal with individual data records
>>> import boto
>>> ml = boto.connect_machinelearning()
>>> ml.predict(
ml_model_id=’my_model',
predict_endpoint=’example_endpoint’,
record={’key1':’value1’, ’key2':’value2’})
{
'Prediction': {
'predictedValue': 13.284348,
'details': {
'Algorithm': 'SGD',
'PredictiveModelType': 'REGRESSION’
}
}
}

45. Architecture patterns for
smart applications

46. Batch predictions with EMR
Query for predictions with
Amazon ML batch API
Process data
with EMR
Raw data in S3
Aggregated data
in S3
Predictions
in S3 Your application

47. Batch predictions with Amazon Redshift
Structured data
in Amazon Redshift
Load predictions into
Amazon Redshift
-or-
Read prediction results
directly from S3
Predictions
in S3
Query for predictions with
Amazon ML batch API
Your application

48. Real-time predictions for interactive applications
Your application
Query for predictions with
Amazon ML real-time API

49. Adding predictions to an existing data flow
Your application
Amazon
DynamoDB
+
Trigger event with Lambda
+
Query for predictions with
Amazon ML real-time API

50. Architecture for Promotions personal
recommendation

51. Focus on the Promotions serving subsystem

52. Q&A
aws.amazon.com/machine-learning

53. Thank You!
Guy Ernest - gernest@amazon.com