AWS Certified Data Analytics Specialty 2021 - Hands-On! - [Exercise] Amazon Machine Learning - Part 1

The video tutorial guides viewers through predicting order quantities using AWS services. It covers setting up a data pipeline with EC2, Kinesis, and S3, and using AWS Machine Learning to create regression models. The tutorial explains schema preparation, data source configuration, and model evaluation, emphasizing the distinction between categorical and numeric data types.

What is the primary purpose of using Amazon Machine Learning in the context of the video?

• To predict order quantities for new orders

• To manage EC2 instances

• To store data in S3

• To create deep neural networks

Which AWS service is primarily used to build regression models as per the video?

• Amazon SageMaker

• Amazon Machine Learning

• Amazon Comprehend

• Amazon Rekognition

What type of data is required to be uploaded to S3 for the machine learning model?

• CSV

• JSON

• HTML

• XML

In the context of the video, what is the significance of a 'categorical' data type?

• It is used for date formats

• It represents data where the order of numbers has no meaning

• It is used for text data only

• It represents data with meaningful numerical order

What is the target variable in the machine learning model discussed in the video?

• Invoice Number

• Quantity

• Description

• SKU

What is the purpose of an optional row identifier in the machine learning model setup?

• To improve model accuracy

• To enhance data security

• To provide context for predictions

• To categorize data

What is the default evaluation split percentage used in the video for training and testing the model?

• 50%

• 30%

• 20%

• 40%