SlideShare a Scribd company logo
1 of 30
Download to read offline
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Machine Learning and Predictive
Quality Management
Madhu Raman
WW Lead ML Industry Programs
Amazon Web Services
A I M 3 1 1
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Edouard Kachelmann
Solutions Architect
Amazon Web Services
Machine Learning and Predictive
Quality Management
Madhu Raman
WW Lead ML Industry Programs
Amazon Web Services
A I M 3 1 1
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Machine Learning and Predictive
Quality Management
A I M 3 1 1
Madhu Raman
WW Lead ML Industry Programs
Amazon Web Services
Edouard Kachelmann
Solutions Architect
Amazon Web Services
Vikrant Kahlir
Enterprise Solutions Architect
Amazon Web Services
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Agenda
Ultrasonic flow meter PQM
AMI access, setup, and launch
Data ingest and transformation
Machine learning for PQM
Solution deployment
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Builder session repeats
Tuesday, November 27
Machine Learning and Predictive Quality Management
8:30 – 9:30 a.m. | Mirage, Grand Ballroom B, Table 5, T1
Day of Week, Month Day
Session Title
Time – Time | Location
Day of Week, Month Day
Session Title
Time – Time | Location
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Related breakouts
Tuesday, November 27
Machine Learning and Excess Stock Inventory Prediction
1 – 2 p.m. | Aria West, Level 3, Starvine 3, Table 9, T1
Monday, November 26
ADT 303 ML for Real-Time Self-Service Trend Detection & Root Cause Analysis
11:30 a.m. – 12:30 p.m. | Aria West, Level 3, Starvine 3, Table 2, T1
Tuesday, November 27
AIM 309 Machine Learning and Predicting Risk
11 a.m. – noon | Aria West, Level 3, Starvine 3, Table 5, T1
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Framing our predictive quality management problem
• From refined products to heavy crude, four-path ultrasonic flow meters
offer the capability to minimize measurement uncertainty of liquid
hydrocarbons.
• Electronics detect changing flow dynamics and help operators pinpoint
issues, including blockages upstream of the meter and abnormal flow
profiles, to minimize measurement uncertainty.
• There is a major focus on cost-reduction in the O&G and P&U industries.
This has initiated increased focus on metering. If a flow meter is not
healthy, the measurement uncertainty may increase significantly in the
period before repair or replacement. This increases the risk of loss of
income from the exported oil, risks related to measurement uncertainty,
and meter failure and production shutdown.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Framing our predictive quality management problem
• We are predicting the health of the
ultrasonic flow meter (USM) based on
the measurement of parameters
reported by it while in operation.
• Data adopted from UCI Machine
Learning Repository, contribution from
Coventry University and National
Engineering Laboratory UK
Citation: K. S. Gyamfi, J. Brusey, A. Hunt, E. Gaura,
“Linear dimensionality reduction for classification
via a sequential Bayes error minimisation with an
application to flow meter diagnostics,” Expert
Systems with Applications (IF: 3.928), September
2017.
1. Profile factor, symmetry, and crossflow
2. Flow velocity in each of the four paths
3. Speed of sound in each of the four paths
4. Signal strength at both ends of each of the four paths
5. Signal quality at both ends of each of the four paths
6. Gain at both ends of each of the four paths
7. Transit time at both ends of each of the four paths
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Build on
You can access our
resource site, which has
everything you need
to build the solution
example described in this
session. You can use
these resources now or
at a later time to build
on AWS.
1. Head over to the URL page.
Use the Step by step Lab
Instructions to build your
solution example.
2. FAQ provides deployment
instructions.
http://2018-reinvent-builders-session-aim311.s3-website-us-east-1.amazonaws.com/
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Access
The analytics platform
AMI will be used in
today’s session.
Deployment
instructions for your
ML workflows using
Server AMI is included
in the step-by-step
instructions.
Follow links at URL
shown for setup and
access instructions.
http://2018-reinvent-builders-session-aim311.s3-website-us-east-1.amazonaws.com/
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
How to solve
We will follow these
steps:
1. Ingest and partition your
data
2. Learn from the data and
create a model
3. Apply predictor model and
determine a score
Connect to S3 data
and transform
+
Partition data and
train your model
+ Apply and score your
model
Build a decision tree model.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Ingest & transform
We ingest the data and
associate “colors” with
classes of outcomes
before partitioning into
70% training and 30%
test sets.
1. Green is healthy
2. Purple implies gas
injection detected
3. Blue implies installation
effects have not yet died
out
4. Red implies that the
health is deteriorating
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Partitioning
• Take from top: Puts the
topmost rows into the first
output table and the
remainder in the second table.
• Linear sampling: Includes the
first and the last row and
selects the remaining rows
linearly over the whole table.
• Draw randomly: Random
sampling of all rows; you may
optionally specify a fixed seed.
• Stratified sampling: Check this
button if you want stratified
sampling. You may optionally
specify a fixed seed.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Model-building
We will use a
classification decision
tree in main memory.
The target attribute
must be nominal. The
other attributes used
for decision-making
can be either nominal
or numerical.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Model prediction
You can examine the
decision tree view.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Evaluation
You can examine how
much better than a
random toss of a coin
your model has
predicted.
We will now use
XGBoost, another type
of machine learning
algorithm, to learn and
predict from the same
data.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Server setup
The KNIME server is
also available for trial
on AWS Marketplace.
Once you launch, you
will find a number of
examples.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Deploy
Examples help you
understand how batch,
RESTful, and various
other capabilities can
be set up visually.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Deploy
The ML workflow can
be executed manually
or automated to be
driven by an event or
to respond to an input
via a RESTful interface.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Deploy
You could simply refer
to your KNIME Server
on AWS via a mount
point within your
KNIME Analytics
Platform.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Deploy
Deployment of your
ML workflow would be
as simple as one-click
drag and drop from
your workspace to start
execution on your
server!
Check out the FAQ
with the Builder
Session material for
more information on
deployment and other
helpful tips.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Key takeaways and next steps
• What we just did on AWS with KNIME does not require data science
and ML experience for you to use on your data
• If you wish to discuss a specific use case for your business, please reach
out to AWS ML Industry Programs (madraman@amazon.com)
• Please complete our session survey: AIM311 Machine Learning and
Predictive Quality Management
Thank you!
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Madhu Raman
madraman@amazon.com
Edouard Kachelmann
kedouard@amazon.com
Vikrant Kahlir
awsvik@amazon.com
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.

More Related Content

What's hot

Cloud Computing in an Edgy World (IOT221-S) - AWS re:Invent 2018
Cloud Computing in an Edgy World (IOT221-S) - AWS re:Invent 2018Cloud Computing in an Edgy World (IOT221-S) - AWS re:Invent 2018
Cloud Computing in an Edgy World (IOT221-S) - AWS re:Invent 2018Amazon Web Services
 
Build Deep Learning Applications Using MXNet and Amazon SageMaker (AIM418) - ...
Build Deep Learning Applications Using MXNet and Amazon SageMaker (AIM418) - ...Build Deep Learning Applications Using MXNet and Amazon SageMaker (AIM418) - ...
Build Deep Learning Applications Using MXNet and Amazon SageMaker (AIM418) - ...Amazon Web Services
 
Human-in-the-Loop for Machine Learning (AIM358-R1) - AWS re:Invent 2018
Human-in-the-Loop for Machine Learning (AIM358-R1) - AWS re:Invent 2018Human-in-the-Loop for Machine Learning (AIM358-R1) - AWS re:Invent 2018
Human-in-the-Loop for Machine Learning (AIM358-R1) - AWS re:Invent 2018Amazon Web Services
 
Build Deep Learning Applications Using PyTorch and Amazon SageMaker (AIM432-R...
Build Deep Learning Applications Using PyTorch and Amazon SageMaker (AIM432-R...Build Deep Learning Applications Using PyTorch and Amazon SageMaker (AIM432-R...
Build Deep Learning Applications Using PyTorch and Amazon SageMaker (AIM432-R...Amazon Web Services
 
Run XGBoost with Amazon SageMaker (AIM335) - AWS re:Invent 2018
Run XGBoost with Amazon SageMaker (AIM335) - AWS re:Invent 2018Run XGBoost with Amazon SageMaker (AIM335) - AWS re:Invent 2018
Run XGBoost with Amazon SageMaker (AIM335) - AWS re:Invent 2018Amazon Web Services
 
Machine Learning Your Eight-Year-Old Would Be Proud Of (AIM390) - AWS re:Inve...
Machine Learning Your Eight-Year-Old Would Be Proud Of (AIM390) - AWS re:Inve...Machine Learning Your Eight-Year-Old Would Be Proud Of (AIM390) - AWS re:Inve...
Machine Learning Your Eight-Year-Old Would Be Proud Of (AIM390) - AWS re:Inve...Amazon Web Services
 
Leadership Session: Digital Advertising - Customer Learning & the Road Ahead ...
Leadership Session: Digital Advertising - Customer Learning & the Road Ahead ...Leadership Session: Digital Advertising - Customer Learning & the Road Ahead ...
Leadership Session: Digital Advertising - Customer Learning & the Road Ahead ...Amazon Web Services
 
Detect Anomalies Using Amazon SageMaker (AIM420) - AWS re:Invent 2018
Detect Anomalies Using Amazon SageMaker (AIM420) - AWS re:Invent 2018Detect Anomalies Using Amazon SageMaker (AIM420) - AWS re:Invent 2018
Detect Anomalies Using Amazon SageMaker (AIM420) - AWS re:Invent 2018Amazon Web Services
 
Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...
Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...
Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...Amazon Web Services
 
Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...
Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...
Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...Amazon Web Services
 
Robocar Rally 2018 (AIM206-R20) - AWS re:Invent 2018
Robocar Rally 2018 (AIM206-R20) - AWS re:Invent 2018Robocar Rally 2018 (AIM206-R20) - AWS re:Invent 2018
Robocar Rally 2018 (AIM206-R20) - AWS re:Invent 2018Amazon Web Services
 
Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...
Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...
Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...Amazon Web Services
 
Hollywood's Cloud-Based Content Lakes: Modernized Media Archives (MAE203) - A...
Hollywood's Cloud-Based Content Lakes: Modernized Media Archives (MAE203) - A...Hollywood's Cloud-Based Content Lakes: Modernized Media Archives (MAE203) - A...
Hollywood's Cloud-Based Content Lakes: Modernized Media Archives (MAE203) - A...Amazon Web Services
 
Detecting Financial Market Manipulation Using Machine Learning (AIM347) - AWS...
Detecting Financial Market Manipulation Using Machine Learning (AIM347) - AWS...Detecting Financial Market Manipulation Using Machine Learning (AIM347) - AWS...
Detecting Financial Market Manipulation Using Machine Learning (AIM347) - AWS...Amazon Web Services
 
Deep Learning Applications Using PyTorch, Featuring Facebook (AIM402-R) - AWS...
Deep Learning Applications Using PyTorch, Featuring Facebook (AIM402-R) - AWS...Deep Learning Applications Using PyTorch, Featuring Facebook (AIM402-R) - AWS...
Deep Learning Applications Using PyTorch, Featuring Facebook (AIM402-R) - AWS...Amazon Web Services
 
Market Prediction Using ML: Experiment with Amazon SageMaker and the Deutsche...
Market Prediction Using ML: Experiment with Amazon SageMaker and the Deutsche...Market Prediction Using ML: Experiment with Amazon SageMaker and the Deutsche...
Market Prediction Using ML: Experiment with Amazon SageMaker and the Deutsche...Amazon Web Services
 
Build Deep Learning Applications Using TensorFlow and Amazon SageMaker (AIM42...
Build Deep Learning Applications Using TensorFlow and Amazon SageMaker (AIM42...Build Deep Learning Applications Using TensorFlow and Amazon SageMaker (AIM42...
Build Deep Learning Applications Using TensorFlow and Amazon SageMaker (AIM42...Amazon Web Services
 
Machine Learning at the Edge (AIM302) - AWS re:Invent 2018
Machine Learning at the Edge (AIM302) - AWS re:Invent 2018Machine Learning at the Edge (AIM302) - AWS re:Invent 2018
Machine Learning at the Edge (AIM302) - AWS re:Invent 2018Amazon Web Services
 
Build an Intelligent Multi-Modal User Agent with Voice and NLU (AIM340) - AWS...
Build an Intelligent Multi-Modal User Agent with Voice and NLU (AIM340) - AWS...Build an Intelligent Multi-Modal User Agent with Voice and NLU (AIM340) - AWS...
Build an Intelligent Multi-Modal User Agent with Voice and NLU (AIM340) - AWS...Amazon Web Services
 
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...Amazon Web Services
 

What's hot (20)

Cloud Computing in an Edgy World (IOT221-S) - AWS re:Invent 2018
Cloud Computing in an Edgy World (IOT221-S) - AWS re:Invent 2018Cloud Computing in an Edgy World (IOT221-S) - AWS re:Invent 2018
Cloud Computing in an Edgy World (IOT221-S) - AWS re:Invent 2018
 
Build Deep Learning Applications Using MXNet and Amazon SageMaker (AIM418) - ...
Build Deep Learning Applications Using MXNet and Amazon SageMaker (AIM418) - ...Build Deep Learning Applications Using MXNet and Amazon SageMaker (AIM418) - ...
Build Deep Learning Applications Using MXNet and Amazon SageMaker (AIM418) - ...
 
Human-in-the-Loop for Machine Learning (AIM358-R1) - AWS re:Invent 2018
Human-in-the-Loop for Machine Learning (AIM358-R1) - AWS re:Invent 2018Human-in-the-Loop for Machine Learning (AIM358-R1) - AWS re:Invent 2018
Human-in-the-Loop for Machine Learning (AIM358-R1) - AWS re:Invent 2018
 
Build Deep Learning Applications Using PyTorch and Amazon SageMaker (AIM432-R...
Build Deep Learning Applications Using PyTorch and Amazon SageMaker (AIM432-R...Build Deep Learning Applications Using PyTorch and Amazon SageMaker (AIM432-R...
Build Deep Learning Applications Using PyTorch and Amazon SageMaker (AIM432-R...
 
Run XGBoost with Amazon SageMaker (AIM335) - AWS re:Invent 2018
Run XGBoost with Amazon SageMaker (AIM335) - AWS re:Invent 2018Run XGBoost with Amazon SageMaker (AIM335) - AWS re:Invent 2018
Run XGBoost with Amazon SageMaker (AIM335) - AWS re:Invent 2018
 
Machine Learning Your Eight-Year-Old Would Be Proud Of (AIM390) - AWS re:Inve...
Machine Learning Your Eight-Year-Old Would Be Proud Of (AIM390) - AWS re:Inve...Machine Learning Your Eight-Year-Old Would Be Proud Of (AIM390) - AWS re:Inve...
Machine Learning Your Eight-Year-Old Would Be Proud Of (AIM390) - AWS re:Inve...
 
Leadership Session: Digital Advertising - Customer Learning & the Road Ahead ...
Leadership Session: Digital Advertising - Customer Learning & the Road Ahead ...Leadership Session: Digital Advertising - Customer Learning & the Road Ahead ...
Leadership Session: Digital Advertising - Customer Learning & the Road Ahead ...
 
Detect Anomalies Using Amazon SageMaker (AIM420) - AWS re:Invent 2018
Detect Anomalies Using Amazon SageMaker (AIM420) - AWS re:Invent 2018Detect Anomalies Using Amazon SageMaker (AIM420) - AWS re:Invent 2018
Detect Anomalies Using Amazon SageMaker (AIM420) - AWS re:Invent 2018
 
Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...
Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...
Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...
 
Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...
Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...
Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...
 
Robocar Rally 2018 (AIM206-R20) - AWS re:Invent 2018
Robocar Rally 2018 (AIM206-R20) - AWS re:Invent 2018Robocar Rally 2018 (AIM206-R20) - AWS re:Invent 2018
Robocar Rally 2018 (AIM206-R20) - AWS re:Invent 2018
 
Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...
Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...
Build, Train, and Deploy ML Models Quickly and Easily with Amazon SageMaker, ...
 
Hollywood's Cloud-Based Content Lakes: Modernized Media Archives (MAE203) - A...
Hollywood's Cloud-Based Content Lakes: Modernized Media Archives (MAE203) - A...Hollywood's Cloud-Based Content Lakes: Modernized Media Archives (MAE203) - A...
Hollywood's Cloud-Based Content Lakes: Modernized Media Archives (MAE203) - A...
 
Detecting Financial Market Manipulation Using Machine Learning (AIM347) - AWS...
Detecting Financial Market Manipulation Using Machine Learning (AIM347) - AWS...Detecting Financial Market Manipulation Using Machine Learning (AIM347) - AWS...
Detecting Financial Market Manipulation Using Machine Learning (AIM347) - AWS...
 
Deep Learning Applications Using PyTorch, Featuring Facebook (AIM402-R) - AWS...
Deep Learning Applications Using PyTorch, Featuring Facebook (AIM402-R) - AWS...Deep Learning Applications Using PyTorch, Featuring Facebook (AIM402-R) - AWS...
Deep Learning Applications Using PyTorch, Featuring Facebook (AIM402-R) - AWS...
 
Market Prediction Using ML: Experiment with Amazon SageMaker and the Deutsche...
Market Prediction Using ML: Experiment with Amazon SageMaker and the Deutsche...Market Prediction Using ML: Experiment with Amazon SageMaker and the Deutsche...
Market Prediction Using ML: Experiment with Amazon SageMaker and the Deutsche...
 
Build Deep Learning Applications Using TensorFlow and Amazon SageMaker (AIM42...
Build Deep Learning Applications Using TensorFlow and Amazon SageMaker (AIM42...Build Deep Learning Applications Using TensorFlow and Amazon SageMaker (AIM42...
Build Deep Learning Applications Using TensorFlow and Amazon SageMaker (AIM42...
 
Machine Learning at the Edge (AIM302) - AWS re:Invent 2018
Machine Learning at the Edge (AIM302) - AWS re:Invent 2018Machine Learning at the Edge (AIM302) - AWS re:Invent 2018
Machine Learning at the Edge (AIM302) - AWS re:Invent 2018
 
Build an Intelligent Multi-Modal User Agent with Voice and NLU (AIM340) - AWS...
Build an Intelligent Multi-Modal User Agent with Voice and NLU (AIM340) - AWS...Build an Intelligent Multi-Modal User Agent with Voice and NLU (AIM340) - AWS...
Build an Intelligent Multi-Modal User Agent with Voice and NLU (AIM340) - AWS...
 
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
 

Similar to AWS ML Predictive Quality Management

Machine learning for developers & data scientists with Amazon SageMaker - AIM...
Machine learning for developers & data scientists with Amazon SageMaker - AIM...Machine learning for developers & data scientists with Amazon SageMaker - AIM...
Machine learning for developers & data scientists with Amazon SageMaker - AIM...Amazon Web Services
 
MLops workshop AWS
MLops workshop AWSMLops workshop AWS
MLops workshop AWSGili Nachum
 
Build Your Recommendation Engine on AWS Today - AWS Summit Berlin 2018
Build Your Recommendation Engine on AWS Today - AWS Summit Berlin 2018Build Your Recommendation Engine on AWS Today - AWS Summit Berlin 2018
Build Your Recommendation Engine on AWS Today - AWS Summit Berlin 2018Yotam Yarden
 
Releasing Mission-Critical Software at Amazon (DEV209-R1) - AWS re:Invent 2018
Releasing Mission-Critical Software at Amazon (DEV209-R1) - AWS re:Invent 2018Releasing Mission-Critical Software at Amazon (DEV209-R1) - AWS re:Invent 2018
Releasing Mission-Critical Software at Amazon (DEV209-R1) - AWS re:Invent 2018Amazon Web Services
 
Chaos Engineering and Scalability at Audible.com (ARC308) - AWS re:Invent 2018
Chaos Engineering and Scalability at Audible.com (ARC308) - AWS re:Invent 2018Chaos Engineering and Scalability at Audible.com (ARC308) - AWS re:Invent 2018
Chaos Engineering and Scalability at Audible.com (ARC308) - AWS re:Invent 2018Amazon Web Services
 
re:Invent Deep Dive on Amazon SageMaker, Amazon Forecast and Amazon Personalise
re:Invent Deep Dive on Amazon SageMaker, Amazon Forecast and Amazon Personalisere:Invent Deep Dive on Amazon SageMaker, Amazon Forecast and Amazon Personalise
re:Invent Deep Dive on Amazon SageMaker, Amazon Forecast and Amazon PersonaliseAmazon Web Services
 
Life of a Code Change to a Tier 1 Service - AWS Online Tech Talks
Life of a Code Change to a Tier 1 Service - AWS Online Tech TalksLife of a Code Change to a Tier 1 Service - AWS Online Tech Talks
Life of a Code Change to a Tier 1 Service - AWS Online Tech TalksAmazon Web Services
 
Quickly and easily build, train, and deploy machine learning models at any scale
Quickly and easily build, train, and deploy machine learning models at any scaleQuickly and easily build, train, and deploy machine learning models at any scale
Quickly and easily build, train, and deploy machine learning models at any scaleAWS Germany
 
Datarobot, 자동화된 분석 적용 시 분석 절차의 변화 및 효용 - 홍운표 데이터 사이언티스트, DataRobot :: AWS Sum...
Datarobot, 자동화된 분석 적용 시 분석 절차의 변화 및 효용 - 홍운표 데이터 사이언티스트, DataRobot :: AWS Sum...Datarobot, 자동화된 분석 적용 시 분석 절차의 변화 및 효용 - 홍운표 데이터 사이언티스트, DataRobot :: AWS Sum...
Datarobot, 자동화된 분석 적용 시 분석 절차의 변화 및 효용 - 홍운표 데이터 사이언티스트, DataRobot :: AWS Sum...Amazon Web Services Korea
 
Remove Undifferentiated Heavy Lifting from CI/CD Toolsets with Corteva Agrisc...
Remove Undifferentiated Heavy Lifting from CI/CD Toolsets with Corteva Agrisc...Remove Undifferentiated Heavy Lifting from CI/CD Toolsets with Corteva Agrisc...
Remove Undifferentiated Heavy Lifting from CI/CD Toolsets with Corteva Agrisc...Amazon Web Services
 
Introducing Amazon SageMaker - AWS Online Tech Talks
Introducing Amazon SageMaker - AWS Online Tech TalksIntroducing Amazon SageMaker - AWS Online Tech Talks
Introducing Amazon SageMaker - AWS Online Tech TalksAmazon Web Services
 
Predictive Scaling for More Responsive Applications (API330) - AWS re:Invent ...
Predictive Scaling for More Responsive Applications (API330) - AWS re:Invent ...Predictive Scaling for More Responsive Applications (API330) - AWS re:Invent ...
Predictive Scaling for More Responsive Applications (API330) - AWS re:Invent ...Amazon Web Services
 
Democratize Data Preparation for Analytics & Machine Learning A Hands-On Lab ...
Democratize Data Preparation for Analytics & Machine Learning A Hands-On Lab ...Democratize Data Preparation for Analytics & Machine Learning A Hands-On Lab ...
Democratize Data Preparation for Analytics & Machine Learning A Hands-On Lab ...Amazon Web Services
 
Fully Realizing the Microservices Vision with Service Mesh (DEV312-S) - AWS r...
Fully Realizing the Microservices Vision with Service Mesh (DEV312-S) - AWS r...Fully Realizing the Microservices Vision with Service Mesh (DEV312-S) - AWS r...
Fully Realizing the Microservices Vision with Service Mesh (DEV312-S) - AWS r...Amazon Web Services
 
From Monolithic to Modern Apps: Best Practices
From Monolithic to Modern Apps: Best PracticesFrom Monolithic to Modern Apps: Best Practices
From Monolithic to Modern Apps: Best PracticesTom Laszewski
 
Architecting for Real-Time Insights with Amazon Kinesis (ANT310) - AWS re:Inv...
Architecting for Real-Time Insights with Amazon Kinesis (ANT310) - AWS re:Inv...Architecting for Real-Time Insights with Amazon Kinesis (ANT310) - AWS re:Inv...
Architecting for Real-Time Insights with Amazon Kinesis (ANT310) - AWS re:Inv...Amazon Web Services
 
Leadership Session: AWS Automotive - Paving the Way for the Future of the Aut...
Leadership Session: AWS Automotive - Paving the Way for the Future of the Aut...Leadership Session: AWS Automotive - Paving the Way for the Future of the Aut...
Leadership Session: AWS Automotive - Paving the Way for the Future of the Aut...Amazon Web Services
 
AWS re:Invent 2018 - Machine Learning recap (December 2018)
AWS re:Invent 2018 - Machine Learning recap (December 2018)AWS re:Invent 2018 - Machine Learning recap (December 2018)
AWS re:Invent 2018 - Machine Learning recap (December 2018)Julien SIMON
 
Amazon SageMaker: ML for Every Developer and Data Scientist - AIM202 - Anahei...
Amazon SageMaker: ML for Every Developer and Data Scientist - AIM202 - Anahei...Amazon SageMaker: ML for Every Developer and Data Scientist - AIM202 - Anahei...
Amazon SageMaker: ML for Every Developer and Data Scientist - AIM202 - Anahei...Amazon Web Services
 
From Monolith to Modern Apps: Best Practices (SRV322-R2) - AWS re:Invent 2018
From Monolith to Modern Apps: Best Practices (SRV322-R2) - AWS re:Invent 2018From Monolith to Modern Apps: Best Practices (SRV322-R2) - AWS re:Invent 2018
From Monolith to Modern Apps: Best Practices (SRV322-R2) - AWS re:Invent 2018Amazon Web Services
 

Similar to AWS ML Predictive Quality Management (20)

Machine learning for developers & data scientists with Amazon SageMaker - AIM...
Machine learning for developers & data scientists with Amazon SageMaker - AIM...Machine learning for developers & data scientists with Amazon SageMaker - AIM...
Machine learning for developers & data scientists with Amazon SageMaker - AIM...
 
MLops workshop AWS
MLops workshop AWSMLops workshop AWS
MLops workshop AWS
 
Build Your Recommendation Engine on AWS Today - AWS Summit Berlin 2018
Build Your Recommendation Engine on AWS Today - AWS Summit Berlin 2018Build Your Recommendation Engine on AWS Today - AWS Summit Berlin 2018
Build Your Recommendation Engine on AWS Today - AWS Summit Berlin 2018
 
Releasing Mission-Critical Software at Amazon (DEV209-R1) - AWS re:Invent 2018
Releasing Mission-Critical Software at Amazon (DEV209-R1) - AWS re:Invent 2018Releasing Mission-Critical Software at Amazon (DEV209-R1) - AWS re:Invent 2018
Releasing Mission-Critical Software at Amazon (DEV209-R1) - AWS re:Invent 2018
 
Chaos Engineering and Scalability at Audible.com (ARC308) - AWS re:Invent 2018
Chaos Engineering and Scalability at Audible.com (ARC308) - AWS re:Invent 2018Chaos Engineering and Scalability at Audible.com (ARC308) - AWS re:Invent 2018
Chaos Engineering and Scalability at Audible.com (ARC308) - AWS re:Invent 2018
 
re:Invent Deep Dive on Amazon SageMaker, Amazon Forecast and Amazon Personalise
re:Invent Deep Dive on Amazon SageMaker, Amazon Forecast and Amazon Personalisere:Invent Deep Dive on Amazon SageMaker, Amazon Forecast and Amazon Personalise
re:Invent Deep Dive on Amazon SageMaker, Amazon Forecast and Amazon Personalise
 
Life of a Code Change to a Tier 1 Service - AWS Online Tech Talks
Life of a Code Change to a Tier 1 Service - AWS Online Tech TalksLife of a Code Change to a Tier 1 Service - AWS Online Tech Talks
Life of a Code Change to a Tier 1 Service - AWS Online Tech Talks
 
Quickly and easily build, train, and deploy machine learning models at any scale
Quickly and easily build, train, and deploy machine learning models at any scaleQuickly and easily build, train, and deploy machine learning models at any scale
Quickly and easily build, train, and deploy machine learning models at any scale
 
Datarobot, 자동화된 분석 적용 시 분석 절차의 변화 및 효용 - 홍운표 데이터 사이언티스트, DataRobot :: AWS Sum...
Datarobot, 자동화된 분석 적용 시 분석 절차의 변화 및 효용 - 홍운표 데이터 사이언티스트, DataRobot :: AWS Sum...Datarobot, 자동화된 분석 적용 시 분석 절차의 변화 및 효용 - 홍운표 데이터 사이언티스트, DataRobot :: AWS Sum...
Datarobot, 자동화된 분석 적용 시 분석 절차의 변화 및 효용 - 홍운표 데이터 사이언티스트, DataRobot :: AWS Sum...
 
Remove Undifferentiated Heavy Lifting from CI/CD Toolsets with Corteva Agrisc...
Remove Undifferentiated Heavy Lifting from CI/CD Toolsets with Corteva Agrisc...Remove Undifferentiated Heavy Lifting from CI/CD Toolsets with Corteva Agrisc...
Remove Undifferentiated Heavy Lifting from CI/CD Toolsets with Corteva Agrisc...
 
Introducing Amazon SageMaker - AWS Online Tech Talks
Introducing Amazon SageMaker - AWS Online Tech TalksIntroducing Amazon SageMaker - AWS Online Tech Talks
Introducing Amazon SageMaker - AWS Online Tech Talks
 
Predictive Scaling for More Responsive Applications (API330) - AWS re:Invent ...
Predictive Scaling for More Responsive Applications (API330) - AWS re:Invent ...Predictive Scaling for More Responsive Applications (API330) - AWS re:Invent ...
Predictive Scaling for More Responsive Applications (API330) - AWS re:Invent ...
 
Democratize Data Preparation for Analytics & Machine Learning A Hands-On Lab ...
Democratize Data Preparation for Analytics & Machine Learning A Hands-On Lab ...Democratize Data Preparation for Analytics & Machine Learning A Hands-On Lab ...
Democratize Data Preparation for Analytics & Machine Learning A Hands-On Lab ...
 
Fully Realizing the Microservices Vision with Service Mesh (DEV312-S) - AWS r...
Fully Realizing the Microservices Vision with Service Mesh (DEV312-S) - AWS r...Fully Realizing the Microservices Vision with Service Mesh (DEV312-S) - AWS r...
Fully Realizing the Microservices Vision with Service Mesh (DEV312-S) - AWS r...
 
From Monolithic to Modern Apps: Best Practices
From Monolithic to Modern Apps: Best PracticesFrom Monolithic to Modern Apps: Best Practices
From Monolithic to Modern Apps: Best Practices
 
Architecting for Real-Time Insights with Amazon Kinesis (ANT310) - AWS re:Inv...
Architecting for Real-Time Insights with Amazon Kinesis (ANT310) - AWS re:Inv...Architecting for Real-Time Insights with Amazon Kinesis (ANT310) - AWS re:Inv...
Architecting for Real-Time Insights with Amazon Kinesis (ANT310) - AWS re:Inv...
 
Leadership Session: AWS Automotive - Paving the Way for the Future of the Aut...
Leadership Session: AWS Automotive - Paving the Way for the Future of the Aut...Leadership Session: AWS Automotive - Paving the Way for the Future of the Aut...
Leadership Session: AWS Automotive - Paving the Way for the Future of the Aut...
 
AWS re:Invent 2018 - Machine Learning recap (December 2018)
AWS re:Invent 2018 - Machine Learning recap (December 2018)AWS re:Invent 2018 - Machine Learning recap (December 2018)
AWS re:Invent 2018 - Machine Learning recap (December 2018)
 
Amazon SageMaker: ML for Every Developer and Data Scientist - AIM202 - Anahei...
Amazon SageMaker: ML for Every Developer and Data Scientist - AIM202 - Anahei...Amazon SageMaker: ML for Every Developer and Data Scientist - AIM202 - Anahei...
Amazon SageMaker: ML for Every Developer and Data Scientist - AIM202 - Anahei...
 
From Monolith to Modern Apps: Best Practices (SRV322-R2) - AWS re:Invent 2018
From Monolith to Modern Apps: Best Practices (SRV322-R2) - AWS re:Invent 2018From Monolith to Modern Apps: Best Practices (SRV322-R2) - AWS re:Invent 2018
From Monolith to Modern Apps: Best Practices (SRV322-R2) - AWS re:Invent 2018
 

More from Amazon Web Services

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...Amazon Web Services
 
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...Amazon Web Services
 
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 FargateAmazon Web Services
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSAmazon Web Services
 
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 Amazon Web Services
 
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...Amazon Web Services
 
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...Amazon Web Services
 
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 WorkloadsAmazon Web Services
 
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 sfatareAmazon Web Services
 
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 NodeJSAmazon Web Services
 
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 webAmazon Web Services
 
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 sfatareAmazon 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 AWSAmazon 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 DeckAmazon Web Services
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without serversAmazon 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
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceAmazon 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
 

AWS ML Predictive Quality Management

  • 1.
  • 2. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Machine Learning and Predictive Quality Management Madhu Raman WW Lead ML Industry Programs Amazon Web Services A I M 3 1 1
  • 3. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Edouard Kachelmann Solutions Architect Amazon Web Services Machine Learning and Predictive Quality Management Madhu Raman WW Lead ML Industry Programs Amazon Web Services A I M 3 1 1
  • 4. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Machine Learning and Predictive Quality Management A I M 3 1 1 Madhu Raman WW Lead ML Industry Programs Amazon Web Services Edouard Kachelmann Solutions Architect Amazon Web Services Vikrant Kahlir Enterprise Solutions Architect Amazon Web Services
  • 5. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Agenda Ultrasonic flow meter PQM AMI access, setup, and launch Data ingest and transformation Machine learning for PQM Solution deployment
  • 6. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Builder session repeats Tuesday, November 27 Machine Learning and Predictive Quality Management 8:30 – 9:30 a.m. | Mirage, Grand Ballroom B, Table 5, T1 Day of Week, Month Day Session Title Time – Time | Location Day of Week, Month Day Session Title Time – Time | Location
  • 7. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Related breakouts Tuesday, November 27 Machine Learning and Excess Stock Inventory Prediction 1 – 2 p.m. | Aria West, Level 3, Starvine 3, Table 9, T1 Monday, November 26 ADT 303 ML for Real-Time Self-Service Trend Detection & Root Cause Analysis 11:30 a.m. – 12:30 p.m. | Aria West, Level 3, Starvine 3, Table 2, T1 Tuesday, November 27 AIM 309 Machine Learning and Predicting Risk 11 a.m. – noon | Aria West, Level 3, Starvine 3, Table 5, T1
  • 8. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 9. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Framing our predictive quality management problem • From refined products to heavy crude, four-path ultrasonic flow meters offer the capability to minimize measurement uncertainty of liquid hydrocarbons. • Electronics detect changing flow dynamics and help operators pinpoint issues, including blockages upstream of the meter and abnormal flow profiles, to minimize measurement uncertainty. • There is a major focus on cost-reduction in the O&G and P&U industries. This has initiated increased focus on metering. If a flow meter is not healthy, the measurement uncertainty may increase significantly in the period before repair or replacement. This increases the risk of loss of income from the exported oil, risks related to measurement uncertainty, and meter failure and production shutdown.
  • 10. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Framing our predictive quality management problem • We are predicting the health of the ultrasonic flow meter (USM) based on the measurement of parameters reported by it while in operation. • Data adopted from UCI Machine Learning Repository, contribution from Coventry University and National Engineering Laboratory UK Citation: K. S. Gyamfi, J. Brusey, A. Hunt, E. Gaura, “Linear dimensionality reduction for classification via a sequential Bayes error minimisation with an application to flow meter diagnostics,” Expert Systems with Applications (IF: 3.928), September 2017. 1. Profile factor, symmetry, and crossflow 2. Flow velocity in each of the four paths 3. Speed of sound in each of the four paths 4. Signal strength at both ends of each of the four paths 5. Signal quality at both ends of each of the four paths 6. Gain at both ends of each of the four paths 7. Transit time at both ends of each of the four paths
  • 11. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Build on You can access our resource site, which has everything you need to build the solution example described in this session. You can use these resources now or at a later time to build on AWS. 1. Head over to the URL page. Use the Step by step Lab Instructions to build your solution example. 2. FAQ provides deployment instructions. http://2018-reinvent-builders-session-aim311.s3-website-us-east-1.amazonaws.com/
  • 12. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 13. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Access The analytics platform AMI will be used in today’s session. Deployment instructions for your ML workflows using Server AMI is included in the step-by-step instructions. Follow links at URL shown for setup and access instructions. http://2018-reinvent-builders-session-aim311.s3-website-us-east-1.amazonaws.com/
  • 14. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. How to solve We will follow these steps: 1. Ingest and partition your data 2. Learn from the data and create a model 3. Apply predictor model and determine a score Connect to S3 data and transform + Partition data and train your model + Apply and score your model Build a decision tree model.
  • 15. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 16. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Ingest & transform We ingest the data and associate “colors” with classes of outcomes before partitioning into 70% training and 30% test sets. 1. Green is healthy 2. Purple implies gas injection detected 3. Blue implies installation effects have not yet died out 4. Red implies that the health is deteriorating
  • 17. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Partitioning • Take from top: Puts the topmost rows into the first output table and the remainder in the second table. • Linear sampling: Includes the first and the last row and selects the remaining rows linearly over the whole table. • Draw randomly: Random sampling of all rows; you may optionally specify a fixed seed. • Stratified sampling: Check this button if you want stratified sampling. You may optionally specify a fixed seed.
  • 18. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 19. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Model-building We will use a classification decision tree in main memory. The target attribute must be nominal. The other attributes used for decision-making can be either nominal or numerical.
  • 20. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Model prediction You can examine the decision tree view.
  • 21. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Evaluation You can examine how much better than a random toss of a coin your model has predicted. We will now use XGBoost, another type of machine learning algorithm, to learn and predict from the same data.
  • 22. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 23. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Server setup The KNIME server is also available for trial on AWS Marketplace. Once you launch, you will find a number of examples.
  • 24. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Deploy Examples help you understand how batch, RESTful, and various other capabilities can be set up visually.
  • 25. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Deploy The ML workflow can be executed manually or automated to be driven by an event or to respond to an input via a RESTful interface.
  • 26. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Deploy You could simply refer to your KNIME Server on AWS via a mount point within your KNIME Analytics Platform.
  • 27. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Deploy Deployment of your ML workflow would be as simple as one-click drag and drop from your workspace to start execution on your server! Check out the FAQ with the Builder Session material for more information on deployment and other helpful tips.
  • 28. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Key takeaways and next steps • What we just did on AWS with KNIME does not require data science and ML experience for you to use on your data • If you wish to discuss a specific use case for your business, please reach out to AWS ML Industry Programs (madraman@amazon.com) • Please complete our session survey: AIM311 Machine Learning and Predictive Quality Management
  • 29. Thank you! © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Madhu Raman madraman@amazon.com Edouard Kachelmann kedouard@amazon.com Vikrant Kahlir awsvik@amazon.com
  • 30. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.