Welcome to Manning India!

We are pleased to be able to offer regional eBook pricing for Indian residents.
All eBook prices are discounted 40% or more!
Machine Learning for Business
Using Amazon SageMaker and Jupyter
Doug Hudgeon, Richard Nichol
  • MEAP began September 2018
  • Publication in January 2020 (estimated)
  • ISBN 9781617295836
  • 300 pages (estimated)
  • printed in black & white

This book is an excellent introduction to machine learning for beginners using real-world examples from the business world that people will actually be able to apply in their day-to-day jobs.

Dary Merckens
  • Imagine predicting which customers are thinking about switching to a competitor or flagging potential process failures before they happen
  • Think about the benefits of forecasting tedious business processes and back-office tasks
  • Envision quickly gauging customer sentiment from social media content (even large volumes of it).
  • Consider the competitive advantage of making decisions when you know the most likely future events
Machine learning can deliver these and other advantages to your business, and it’s never been easier to get started!
Table of Contents detailed table of contents

Part 1: Machine learning in business

1 How machine learning applies to your business

1.1 Why are our business systems so terrible?

1.2 Why is automation important now?

1.2.1 What is productivity?

1.2.2 How will machine learning improve productivity?

1.3 How do machines make decisions?

1.3.1 People: Rules-based or not?

1.3.2 Can I trust a pattern-based answer?

1.3.3 How can machine learning improve our business systems?

1.4 Can a machine help Karen make decisions?

1.4.1 Target variables

1.4.2 Features

1.5 How does a machine learn?

1.6 Getting approval in your company to use machine learning to make decisions

1.7 The tools

1.7.1 What is AWS and SageMaker, and how can they help me?

1.7.2 What is a Jupyter notebook?

1.8 Setting up SageMaker in preparation for tackling the scenarios in chapters 2 to 8

1.9 The time to act is now

1.10 Summary

Part 2: Six scenarios: Machine learning in business

2 Should you send a purchase order to a technical approver?

2.1 The decision

2.2 The data

2.3 Putting on your training wheels

2.4 Run the Jupyter notebook and make predictions

2.4.1 Part 1: Load and examine the data

2.4.2 Part 2: Get the data into the right shape

2.4.3 Part 3: Create training, validation, and test datasets

2.4.4 Part 4: Train the model

2.4.5 Part 5: Host the model

2.4.6 Part 6: Test the model

2.5 Delete the endpoint and shut down your notebook instance

2.5.1 Deleting the endpoint

2.5.2 Shutting down the notebook instance

2.6 Summary

3 Should you call a customer because they are at risk of churning?

3.1 What are you making decisions about?

3.2 The process flow

3.3 Preparing the dataset

3.3.1 Transformation 1: Normalize the data

3.3.2 Transformation 2: Calculate the change from week to week

3.4 XGBoost primer

3.4.1 How XGBoost works

3.4.2 How does the machine learning model determine whether the function is getting better or getting worse?

3.5 Getting ready to build the model

3.5.1 Upload a dataset to S3

3.5.2 Set up a notebook on SageMaker

3.6 The code

3.6.1 Part 1: Load and examine the data

3.6.2 Part 2: Get the data into the right shape

3.6.3 Part 3: Create training, validation, and test datasets

3.6.4 Part 4: Train the model

3.6.5 Part 5: Host the model

3.6.6 Part 6: Test the model

3.7 Delete the endpoint and shut down your notebook instance

3.7.1 Deleting the endpoint

3.7.2 Shutting down the notebook instance

3.8 Check to make sure the endpoint is deleted

3.9 Summary

4 Should an incident be escalated to your support team

4.1 What are you making decisions about?

4.2 The process flow

4.3 Preparing the dataset

4.4 NLP (natural language processing)

4.4.1 Creating word vectors

4.4.2 Deciding how many words to include in each group

4.5 What is BlazingText and how does it work?

4.6 Getting ready to build the model

4.6.1 Upload a dataset to S3

4.6.2 Set up a notebook on SageMaker

4.7 The code

4.7.1 Part 1: Load and examine the data

4.7.2 Part 2: Get the data into the right shape

4.7.3 Part 3: Create training and validation datasets

4.7.4 Part 4: Train the model

4.7.5 Part 5: Host the model

4.7.6 Part 6: Test the model

4.8 Delete the endpoint and shut down your notebook instance

4.8.1 Deleting the endpoint

4.9 Check to make sure the endpoint is deleted

4.10 Summary

5 Should you question an invoice sent by a supplier?

5.1 What are you making decisions about?

5.2 The process flow

5.3 Preparing the dataset

5.4 What are anomalies

5.5 Supervised versus unsupervised machine learning

5.6 What is Random Cut Forest and how does it work?

5.6.1 Sample 1

5.6.2 Sample 2

5.7 Getting ready to build the model

5.7.1 Upload a dataset to S3

5.7.2 Set up a notebook on SageMaker

5.8 The code

5.8.1 Part 1: Load and examine the data

5.8.2 Part 2: Get the data into the right shape

5.8.3 Part 3: Create training and validation datasets

5.8.4 Part 4: Train the model

5.8.5 Part 5: Host the model

5.8.6 Part 6: Test the model

5.9 Delete the endpoint and shut down your notebook instance

5.9.1 Deleting the endpoint

5.9.2 Shutting down the notebook instance

5.10 Check to make sure the endpoint is deleted

5.11 Summary

6 Forecasting your company’s monthly power usage

6.1 What are you making decisions about?

6.1.1 Introduction to time-series data

6.1.2 Kiara’s time-series data: Daily power consumption

6.2 Load the Jupyter notebook for working with time-series data

6.3 Preparing the dataset: Charting time-series data

6.4 What is a neural network?

6.5 Getting ready to build the model

6.5.1 Upload a dataset to S3

6.5.2 Set up a notebook on SageMaker

6.6 The code

6.6.1 Part 1: Load and examine the data

6.6.2 Part 2: Get the data into the right shape

6.6.3 Part 3: Create training and test datasets

6.6.4 Part 4: Train the model

6.6.5 Part 5: Host the model

6.6.6 Part 6: Make predictions and plot results

6.7 Delete the endpoint and shut down your notebook instance

6.7.1 Deleting the endpoint

6.7.1 Shutting down the notebook instance

6.8 Check to make sure the endpoint is deleted

6.9 Summary

Improving your company’s monthly power usage forecast

7.1 DeepAR’s ability to pick up periodic events

7.3 Incorporating additional datasets into Kiara’s power consumption model

7.4 Getting ready to build the model

7.4.1 Download the notebook we prepared

7.4.2 Set up the folder on SageMaker

7.4.3 Upload notebook to SageMaker

7.4.4 Download the datasets from the S3 bucket

7.4.5 Set up a folder on S3 to hold your data

7.4.6 Upload the datasets to your AWS bucket

7.5 Building the model

7.5.1 Part 1: Setting up the notebook

7.5.2 Part 2: Importing the datasets

7.5.3 Part 3: Getting the data into the right shape

7.5.4 Part 4: Create training and test datasets

7.5.5 Part 5: Configure the model and set up the server to build the model

7.5.6 Part 6: Make predictions and plot results

7.6 Delete the endpoint and shut down your notebook instance

7.6.1 Deleting the endpoint

7.6.2 Shutting down the notebook instance

7.7 Check to make sure the endpoint is deleted

7.8 Summary

Part 3: Moving machine learning into production

Serving predictions over the web

8.1 Why is serving decisions and predictions over the web so difficult?

8.2 Overview of steps for this chapter

8.3 The SageMaker endpoint

8.4 Set up the SageMaker endpoint

8.4.1 Uploading the notebook

8.4.2 Uploading the data

8.4.3 Running the notebook and creating the endpoint

8.5 Setting up the serverless API endpoint

8.5.1 Setting up your AWS credentials on your AWS account

8.5.2 Setting up your AWS credentials on your local computer

8.5.3 Configuring your credentials

8.6 Creating the web endpoint

8.6.1 Installing Chalice

8.6.2 Creating a Hello World API

8.6.3 Adding the code that serves the SageMaker endpoint

8.6.4 Configuring permissions

8.6.5 Updating requirements.txt

8.6.6 Deploying Chalice

8.7 Serve decisions

8.8 Summary

9 Case studies

9.1 Case Study 1: WorkPac

9.1.1 Designing the project

9.1.2 Stage 1: Preparing and testing the model

9.1.3 Stage 2: Implementing proof of concept

9.1.4 Stage 3: Embedding the process into the company’s operations

9.1.5 Next steps

9.1.6 Lessons learned

9.2 Faethm.ai

9.2.1 AI at the core

9.2.2 Using machine learning to improve processes at Faethm

9.2.3 Stage 1: Get the data

9.2.4 Stage 2: Identify the features

9.2.5 Stage 3: Validate the results

9.2.6 Stage 4: Implement in production

9.3 Conclusion

9.4 Summary

Appendixes

Appendix A: Signing up for Amazon AWS

A.1 Signing up for AWS

A.2 AWS Billing overview

Appendix B: Setting up and using S3 to store files

B.1 Set up a bucket in S3

B.1.1 Step 1: Name your bucket

B.1.2 Step 2: Set properties for your bucket

B.1.3 Step 3: Set permissions

B.1.4 Step 4: Review settings

B.2 Set up folders in S3

B.3 Upload files to S3

Appendix C: Setting up and using AWS SageMaker to build a machine learning system

C.1 Getting set up

C.2 Start at the Dashboard

C.3 Create a notebook instance

C.4 Start the notebook instance

C.5 Upload the notebook to the notebook instance

C.6 Run the notebook

Appendix D: Shutting it all down

D.1 Delete the endpoint

D.2 Shut down the notebook instance

Appendix E: Installing Python

About the Technology

Big companies use machine learning—a process which identifies patterns in data and learns from them—to drive important decisions like financial forecasting, targeted product recommendations, and resource planning. Now, easy-to-use tools, well-defined practices, and readily-available services bring the advantages of machine learning to organizations of any size! Bottom line? Companies that don’t use machine learning to gain cost savings, reliability, and efficiency will soon be overtaken by those that do.

About the book

Machine Learning for Business teaches you how to make your company more automated, productive, and competitive by mastering practical, implementable machine learning techniques and tools such as Amazon SageMaker. Thanks to the authors’ down-to-earth style, you’ll easily grok why process automation is so important and why machine learning is key to its success. In this hands-on guide, you’ll work through six end-to-end machine learning scenarios covering business processes in accounts payable, billing, engineering, customer support, and other common tasks. Using Amazon SageMaker (no installation required!), you’ll build and deploy machine learning applications as you practice takeaway skills you’ll use over and over. By the time you’re finished, you’ll confidently identify machine learning opportunities in your company and implement automated applications that can sharpen your competitive edge!

What's inside

  • Identifying processes suited to machine learning
  • Using machine learning to automate back office processes
  • Six everyday business process projects
  • Using open source and cloud-based tools
  • Case studies for machine learning decision making

About the reader

For technically-inclined business professionals or business developers. No previous experience with automation tools or programming is necessary.

About the authors

Doug Hudgeon runs a business automation consultancy, putting his considerable experience helping companies set up automation and machine learning teams to good use. In 2000, Doug launched one of Australia’s first electronic invoicing automation companies. Richard Nichol has over 20 years of experience as a data scientist and software engineer. He currently specializes in maximizing the value of data through AI and machine learning techniques.

Manning Early Access Program (MEAP) Read chapters as they are written, get the finished eBook as soon as it’s ready, and receive the pBook long before it's in bookstores.
MEAP combo $39.99 pBook + eBook + liveBook
MEAP eBook $27.99 pdf + ePub + kindle + liveBook
Prices displayed in rupees will be charged in USD when you check out.

placing your order...

Don't refresh or navigate away from the page.

FREE domestic shipping on three or more pBooks