7 Leading

Machine Learning
Use Cases
How today’s businesses are using
machine learning to achieve fast,
efficient, measurable results
Solve your most common
business challenges with
machine learning
Machine learning has moved beyond the hype to become Second, you’ll want to find a use case that is rich in data
a meaningful driver of value for many organizations. that you already have. A good business use case with no
Over two thirds of the businesses that have fully data leads to frustrated data scientists.
embraced artificial intelligence (AI) say the technology
has created a better customer experience, improved Lastly, you’ll want to evaluate whether your business
decision-making, increased their productivity and problem actually requires machine learning for success
allowed them to innovate while achieving cost savings.1 and whether machine learning will result in better
outcomes than your traditional approach. These
While it’s clear that machine learning is an essential part outcomes might be realized as cost reduction, increased
of business transformation, many organizations struggle employee productivity, or improved experiences for your
to understand where to apply machine learning for the end customers.
most impact. Selecting the right machine learning use
case requires you to consider a number of factors. The best way to satisfy all of these criteria is to ensure
that technical experts and domain experts are working
First, you need to find a balance between optimal hand in hand on your machine learning project.
business value and speed. A proof of concept built by Technical experts can conduct feasibility assessments,
a siloed data scientist is not likely to generate much and domain experts will ensure the solution is solving a
enthusiasm for machine learning in an organization. real business problem and will have a real impact.
What is more apt to attract the needed commitment and
funding is showing how machine learning can address
the practical issues your organization currently faces.
Furthermore, you’ll want to find something that can
be accomplished in 6–10 months so that you don’t lose
momentum. This is especially true if this is your first
foray into machine learning.

1 https://www.pwc.com/us/en/tech-effect/ai- 2
analytics/ai-predictions.html
 7
Starting with the right use case
leading use cases
is key to organizational buy-in
In this eBook, we have outlined seven use cases where AWS customers 1 Improve employee productivity ›
have successfully applied machine learning. These use cases will
strengthen your business case for wider adoption of machine learning, 2 Automate document data extraction and analysis ›
and you can apply them to kick-start your machine learning journey or
add them to your current strategy. 3 Add contact center intelligence ›

What makes a good machine learning use case? 4 Personalize customer recommendations ›

• Solves a real problem for your business—one that’s important 5 Increase the value of media assets ›
enough to get attention, support, and adoption
6 Improve business operations with forecasting ›
• Leverages sources of untapped data
• Increases performance, reduces costs, and/or improves your end- 7 Identify fraudulent online activities ›
customer experiences
• Includes technical experts to conduct feasibility assessments and
domain experts to ensure the solution will be used
• Can be completed in 6–10 months

When you are ready to deploy your use case, you have the choice
of using one or more fully-managed AWS AI Services to quickly
get started and easily integrate intelligence into your applications.
Or, if you want to develop your own models, you can use Amazon
SageMaker—a solution that provides you with all the machine learning
tools you’ll need in a single service.

3
1 Ideal for all industries

Here are some specific

Improve employee productivity by quickly WOODSIDE ENERGY LTD.
questions
and easily finding to accurate
consider information “(With Amazon Kendra,) we’re now able to precisely
when evaluating search our most valuable project engineering
documents. This step-change in cognitive capability
infrastructure:
Employees who have fast, easy access to accurate data are more
productive. In a 2019 study by The Economist, executives identified will enable better, faster decision-making to improve
“ease of access to information required to get work done” as the our operations and the working lives of our people.”
#1 way in which technology can drive employee engagement
and productivity.2 Shelley Kalms, Chief Digital Officer

Your employees can search for the information they need by asking
natural-language questions through Amazon Kendra—a highly BAKER TILLY DIGITAL | LABS
accurate intelligent search service powered by machine learning. This
“By using (Amazon) Kendra, our clients are able to
is much faster and more efficient than traditional keyword search, and
the service is easy to deploy for businesses of all sizes. The resulting
surface relevant information 10 times faster when
boost in productivity helps accelerate research while improving compared to SharePoint full text search, quickly
decision making—and strengthens your business case for wider surfacing an answer previously not possible with
machine learning adoption. keyword search and connecting them to relevant
content across an enterprise-wide repository, or
Learn more ›
providing marketing managers quick access to
crucial research on customer behavior.”

Ollie East, Director of Advanced Analytics and Data Engineering, and

Tom Puch, Sr. Manager

2 https://theexperienceofwork.economist.com/pdf/Citrix_The_Experience_of_Work_
4
BriefingPaper.pdf
2 Ideal for Financial Services, Healthcare and Life Sciences,
Accounting, Education, Government, Legal, Oil and Gas
Here are some specific
Make faster decisions by automatically
questions
extracting andto consider
analyzing data from documents ASSENT COMPLIANCE

when evaluating “Amazon Textract’s OCR technology enabled us to

process…documents while Amazon Comprehend
infrastructure:
The millions of documents created by your organization contain a
treasure trove of insights waiting to be leveraged. Unfortunately, was able to extract custom entities. (Using) Amazon
manually processing the ever-growing volumes of information to make Augmented AI, we were able to have our teams review
them easy to access and search is a cumbersome, costly task. Using
documents in a given accuracy range and help train
machine learning, your organization can gain timely access to the
our next model iteration. Combining these services…
information contained in your documents, leading to new insights that
inform your business decisions. (saved) our customers hundreds of hours in manually
reviewing documents.”
For organizations looking to easily activate intelligent document
processing today, AWS offers three services that can be deployed Corey Peters, Senior Software Developer
individually or in any combination. Amazon Textract automatically
extracts handwriting, printed text, and data from scanned documents.
Amazon Comprehend is a natural language processing (NLP) service
THOMSON REUTERS
that uses machine learning to find insights and relationships in text. “Our solution required several iterations of deep
And Amazon Augmented AI (Amazon A2I) provides built-in human learning configurations at scale. Amazon SageMaker
review workflows to ensure accuracy of the data.
enabled us to design a natural language processing
You can also quickly and efficiently develop your own machine capability in the context of a question answering
learning models for text extraction and analysis with Amazon application…successfully allowing (our customers) to
SageMaker, a fully managed service that helps data scientists and
simplify and derive more value from their work.”
developers build, train, and deploy machine learning models. This
service provides several built-in machine learning algorithms—such Khalid Al-Kofahi, AI and Cognitive Computing - Thomson Reuters Center
as BlazingText and Linear Learner—that are optimized for text
classification, NLP, and optical character recognition (OCR).

Learn more ›

5
3 Ideal for all industries

Here are some specific

Add intelligence to your contact center to VONAGE
questions
improve service toandconsider
reduce cost “With Amazon Lex, we can empower Vonage
when evaluating customers to choose how and where they will
engage with us—building intelligent interaction
infrastructure:
Improving the customer service experience is one of the best ways to
differentiate your brand—and to demonstrate the value of machine paths into existing voice and messaging channels.”
learning. Successful organizations treat their customer contact center as an
asset that is crucial to success rather than viewing it solely as a cost center. Alan Masarek, Chief Executive Officer

Machine learning can help to transform a contact center into a profit center
by reducing call wait times, improving agent productivity and satisfaction, GE APPLIANCES
lowering costs, and helping to identify business improvement opportunities. “Using Amazon Connect, Amazon Lex, and Amazon
AWS offers several flexible options to easily add intelligence to your Polly, we can automate simple (call center) tasks,
contact center. Amazon Connect is an easy-to-use omnichannel cloud such as looking up product information, taking
contact center that helps companies provide superior customer service at a down customer details, and answering common
lower cost. Contact Lens for Amazon Connect is a set of machine learning
questions before an agent answers (the phone).”
capabilities integrated into Amazon Connect that allows contact center
supervisors to better understand the sentiment, trends, and compliance Byron Guernsey, Chief Strategist
risks of customer conversations to effectively train agents, replicate
successful interactions, and identify crucial company and product feedback.

If your organization already has a contact center solution in place, AWS

Contact Center Intelligence (CCI) solutions offer a variety of ways to
quickly and cost-effectively add AI to your contact center. These solutions,
available through participating AWS Partner Network (APN) partners, allow
customers to benefit from AWS machine learning-powered solutions to
enhance self-service, analyze calls in real time to assist agents, and learn
from all contact center interactions with post-call analytics.

Learn more ›

6
4 Ideal for Retail, Media and Entertainment, Travel and Hospitality,
Education, Financial Services, Government, Healthcare, Software
Here are some specific and Internet
Make personalized recommendations to
questions
increase customer to consider
engagement
LOTTE MART
when evaluating “(With Amazon Personalize,) we have seen a 5x
infrastructure:
Consumers today expect real-time, personalized experiences across digital
channels as they consider, purchase, and use products and services. increase in response to recommended products…
(increasing) the number of products that the
Machine learning can help you deliver these highly personalized experiences,
customer has never purchased before up to 40%.”
resulting in improvements in customer engagement, conversion, revenue,
and margin. AWS offers machine learning solutions that deliver higher- Jaehyun Shin, Big Data Team Leader
quality personalized experiences across digital channels—all tailored to
your business needs.
ZAPPOS
If you want to quickly get started with personalization today, you can
“We are…using analytics and machine learning
use Amazon Personalize—a fully managed service that leverages over
20 years of personalization experience at Amazon. Amazon Personalize solutions to personalize sizing and search results for
makes it easy to develop applications for a wide array of personalization individual users. AWS services (including Amazon
use cases, including product or content recommendations, individualized SageMaker) allow (our) engineers to focus on
search results, and customized marketing communications—with no
improving performance and results rather than
machine learning expertise required.
DevOps overhead.”
Or, if you want to develop your own machine learning models for
Ameen Kazerouni, Head of Machine Learning Research and Platforms
recommendation engines, you can use Amazon SageMaker—a fully
managed service that helps data scientists and developers build, train, and
deploy machine learning models quickly. You can use built-in algorithms
such as factorization machines or XGBoost, both of which are optimized for
personalization, to readily train and deploy models. You can also bring your
own algorithms or models or select from the hundreds of algorithms and
pre-trained models available at the AWS Marketplace.

Learn more ›

7
5 Ideal for Financial Services, Healthcare and Life Sciences,
Accounting, Education, Government, Legal, Oil and Gas
Here are some specific
Analyze media assets to increase value
questions
and create newto consider
insights NASCAR

when evaluating “We selected Amazon Transcribe to power the

captioning of NASCAR’s VOD content…spanning 195
infrastructure:
Media assets, such as audio and video, are invaluable in offering an enhanced
customer experience across entertainment, professional sports, education, and countries and 29 languages. Since implementing
other industries. The value of these assets can be greatly increased through Amazon Transcribe, we automatically add captions
targeting, personalization, and improved monetization. Unfortunately, many
to 99% of our VOD content and spend 97% less than
companies struggle to optimize their media to fully take advantage of this content.
what we had originally estimated.”
Applying machine learning to this problem can provide benefits across four key
Patrick Carroll, Senior Director, Development
areas—easily enable better content search and discovery, increase accessibility
through captioning and localization, improve content monetization, and
improve media compliance and moderation. AWS offers several machine
NFL MEDIA
learning solutions that can help you intelligently manage your media assets.
“Amazon Rekognition…significantly improves
AWS Media Insights Engine leverages Amazon Rekognition, Amazon the speed in which we can search for content and
Transcribe, and Amazon Translate to dramatically accelerate your ability to
enables us to automatically tag elements that
index rich content—so you can quickly make it available for content searches,
ad optimization, subtitling and localization, content moderation, compliance required manual efforts before.”
adherence, and highlight generation. Amazon Rekognition enables faster,
Brad Boim, Senior Director, Post Production and Asset Management
easier image and video analysis with custom labeling to further enhance
content indexing and retrieval. Amazon Transcribe enables efficient conversion
of audio speech into text to create rich metadata indexes for search and
discovery. Combining Amazon Transcribe with Amazon Translate provides
content publishers a workstream to easily caption and translate videos to
remove barriers and increase reach and accessibility. Media2Cloud helps
you set up a serverless, end-to-end content ingest and analysis workflow,
streamlining the process of moving media assets to the cloud. It uses machine
learning to extract and analyze the metadata needed to build the viewing
experiences your customers want.

Learn more ›

8
6 Ideal for Energy and Utilities, Industrial, Manufacturing, Retail,
Software and Internet, Startups, Telecommunications, Travel aNd
Here are some specific Hospitality
Go beyond tracking business metrics
questions todetecting
by automatically consider anomalies, DOMINO'S PIZZA ENTERPRISES LIMITED
when evaluating
identifying the root cause, and accurately “We knew that by using AWS Services (including
forecasting their future values
infrastructure: Amazon SageMaker) we could…give our stores a
glimpse into the future by predicting what pizzas
Organizations across all industries have widely adopted business metrics would be ordered next. Customers are getting their
and Key Performance Indicators (KPI) to measure their performance and pizza faster, hotter, and fresher because of the
track their progress against their business goals. From sales to customer improvements we’ve put into place.”
engagement, from inventory to supply/demand, from web metrics to
project management data, and from social media to machine-generated Michael Gillespie, Chief Digital and Technology Officer
data – regardless of its type - business metrics are key to understand how
companies are performing.
HEROLEADS
While companies use scorecards and dashboards to periodically review
“By integrating Amazon Forecast, we will free up the
their key business metrics, Amazon Lookout for Metrics automatically
identifies anomalies in business data, such as a sudden dip in sales team to focus on more value-added work, expand
revenue or customer acquisition rate, and more importantly, identifies the reach of our models to be used by other teams,
the root cause and sends alerts to the metrics owners. and improve our forecast model accuracy to 99%.
(Amazon Forecast provides) faster insights, improved
Forecasting what customers want, how much of it they want, and when
they will want it is vital to any organization's success. Supply chain, sales, predictability, performance alerting systems, dynamic
finance, and other business units are dependent upon accurate demand budget planning, and more accurate investment models.”
metrics to satisfy customers, better manage the inventory, and optimize
Amit Das, Lead Data Engineer
cash flow. Amazon Forecast automated processes help you create a
customer machine learning model in hours with no machine learning
experience required, while Amazon SageMaker can be used by those
organizations that want to develop their own forecasting models.

Organizations that want to develop their own machine learning models

for forecasting can use Amazon SageMaker, a fully managed service that
helps data scientists and developers build, train, and deploy machine
learning models quickly.

9
7 Ideal for E-Commerce, Finance, Retail

Here are some specific

Make it easy to identify potential fraudulent EULER HOMES
questions
online activities to consider “With administrative and financial data of more than
when evaluating 30 million companies, it can be challenging to detect
cyber fraud before it impacts business operations.
infrastructure:
Around the globe, billions of dollars are lost each year to online fraud. 3

Many applications that are designed to protect against potential online (Using Amazon SageMaker,) we were able to launch
fraud rely on business rules that are not keeping pace with the ever- a new internal service in seven months and can now
changing tactics of bad actors.
identify URL squatting fraud within 24 hours.”
Fraud detection is a good application for machine learning for three
Luis Leon, IT Innovation Advisor
primary reasons. First, it addresses a problem that’s rich in data and can
benefit from pattern identification within datasets. Second, it can achieve
results that are nearly impossible to accomplish through human input VACASA
alone. Finally, these results are easily quantifiable in financial terms,
which can help foster executive buy-in for machine learning across “We’re excited about the introduction of Amazon
the organization. Fraud Detector because it means we can more easily
use advanced machine learning techniques to
Amazon Fraud Detector leverages machine learning and more than 20
accurately detect fraudulent (vacation) reservations.
years of fraud detection expertise from Amazon to catch more potential
online fraud faster and easier. It puts your data at the center of your Protecting our ‘front door’ from potential harm
solution and makes it simpler to identify and prevent fraud—with no enables us to focus on making the vacation rental
prior machine learning experience necessary. experience seamless and worry-free.”
For fraud detection, Amazon SageMaker offers built-in algorithms, such Eric Breon, Founder and CEO
as Random Cut Forest and XGBoost, and hundreds of algorithms and pre-
trained models available through the AWS Marketplace, allowing you to
develop fraud detection solutions in days.

Learn more ›

3 https://www.javelinstrategy.com/coverage-area/2019-identity-fraud-report-
10
fraudsters-seek-new-targets-and-victims-bear-brunt
Start or expand your
machine learning
journey now
With the use cases in this eBook, you can leverage machine learning to boost
productivity, make smarter use of your data, meet customer demands more
effectively and efficiently, enhance customer experiences and satisfaction,
make better decisions faster, and reduce the frequency and impact of fraud.

We chose to highlight these seven use cases because our customers

are achieving success with them today—and because they fulfill all the
requirements you should look for when identifying a suitable application for
machine learning. These use cases can be completed in a matter of months,
solve real business problems, leverage sources of untapped data, and increase
performance, reduce costs, and/or improve end-customer experiences. They
lend themselves to the inclusion of technical and domain experts, and—when
properly executed—generate results that gain attention and foster executive
support for wider adoption of machine learning.

The business potential of machine learning goes far beyond these seven
use cases. With the broadest and deepest set of machine learning services
available today, AWS can help you apply machine learning in a wide variety of
ways that transform your business—allowing you to push innovation to new
heights and reimagine the possibilities of what your organization can achieve.

Learn more about AWS machine learning ›

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved.
11