AI News, Amazon Machine Learning – Make Data-Driven Decisions at Scale

Amazon Machine Learning – Make Data-Driven Decisions at Scale

Today, it is relatively straightforward and inexpensive to observe and collect vast amounts of operational data about a system, product, or process.

Not surprisingly, there can be tremendous amounts of information buried within gigabytes of customer purchase data, web site navigation trails, or responses to email campaigns.

The bad news is that you need to find data scientists with relevant expertise in machine learning, hope that your infrastructure is able to support their chosen tool set, and hope (again) that the tool set is sufficiently reliable and scalable for production use.

Properly used, Machine Learning can serve as the basis for systems that perform fraud detection (is this transaction legitimate or not?), demand forecasting (how many widgets can we expect to sell?), ad targeting (which ads should be shown to which users?), and so forth.

You can build and fine-tune predictive models using large amounts of data, and then use Amazon Machine Learning to make predictions (in batch mode or in real-time) at scale.

You can benefit from machine learning even if you don’t have an advanced degree in statistics or the desire to setup, run, and maintain your own processing and storage infrastructure.

For example, if you have rows that represent completed transactions that were either legitimate or fraudulent, each row must contain a column that denotes the result, which is also known as the target variable.

This is a floating point value in the range 0.0 to 1.0 that expresses how often the model predicts the correct answer on data it was not trained with.

you can adjust it up or down based on the relative importance of false positives (predictions that should be false but were predicted as true) and false negatives (predictions that should be true but were predicted as false) in your particular situation.

If you are building a spam filter for email, a false negative will route a piece of spam to your inbox and a false positive will route legitimate mail to your junk folder.

The tradeoffs between false positives and false negatives is going to depend on your business problem and how you plan to make use of the model in a production setting, Amazon Machine Learning in Action Let’s walk through the process of creating a model and generating some predictions using the steps described in the Tutorial section of the Amazon Machine Learning Developer Guide.

This object holds the location of the data, the variable names and types, the name of the target variable, and descriptive statistics for each variable.

Selecting the Redshift option shown above would have given me the option to enter the name of my Amazon Redshift cluster, along with a database name, access credentials, and a SQL query.

In order to select the best customers (those most likely to make a purchase), I clicked on Adjust Score Threshold and bumped up the cut-off value until 5% of the records were expected to pass by predicting a value of “1” for y:

The first value is the predicted y variable (computed by comparing the prediction score against the cut off that I set when I was building the model), and the second is the actual score.

If I am building a real time application and I need to generate predictions as part of a request-response cycle, I can enable the model for real time predictions like this:

Here’s some Java code that retrieves the metadata associated with an ML model (mlModelId in the code), finds the service endpoint in the metadata, makes a real-time prediction, and displays the result: The code will produce output that looks like this: This means that the ML model type was Binary classification, the predicted score was 0.10312237, and based on the prediction threshold associated with the model when the code was run, the predicted response was ‘0’.

AWS re:Invent 2016: Predicting Customer Churn with Amazon Machine Learning (MAC307)

In this session, we take a specific business problem—predicting Telco customer churn—and explore the practical aspects of building and evaluating an Amazon ...

AWS | Full Stack Python | Real time Data Prediction | Machine Learning | Ajay Jatav

This video is about AWS and real time prediction using Python which forms a part of machine learning.

Exploring the Business Use Cases for Amazon Machine Learning - 2017 AWS Online Tech Talks

Learning Objectives: - Learn how to integrate Amazon Machine Learning with applications - Learn how to train a model using Amazon Machine Learning - Learn ...

Introduction to Amazon Machine Learning - Predictive Analytics on AWS

Amazon Machine Learning makes it easy for developers of all skill levels to use machine learning technology. Learn more:

AWS Summit Tel Aviv 2016: Amazon Machine Learning Case Study: Predicting Customer Churn

Learn More: - - - - - - - - - - - - - - - - - Session Language: English We do a deeper dive into Amazon Machine Learning, using a specific ..

How to Train Your Models in the Cloud

Let's discuss whether you should train your models locally or in the cloud. I'll go through several dedicated GPU options, then compare three cloud options; AWS ...

Using Amazon Machine Learning to predict

This video will demonstrate how to use Amazon Machine Learning to predict. It was created by Caio Moreno de Souza from IT4biz Global to help our students ...

AWS SageMaker Deep Learning for Breast Cancer Prediction

A tutorial that llustrates how one can use SageMaker's algorithms for solving applications which require linear models for prediction. For this illustration, we have ...

AWS re:Invent Launchpad 2017 - Amazon SageMaker

Amazon SageMaker is a fully-managed service that enables data scientists and developers to quickly and easily build, train, and deploy machine learning ...

The Best Way to Prepare a Dataset Easily

In this video, I go over the 3 steps you need to prepare a dataset to be fed into a machine learning model. (selecting the data, processing it, and transforming it).