Amazon Machine Learning will provide marketers with greater ability to personalise

Amazon Machine Learning will provide marketers with greater ability to personalise across channels, predict results and ultimately drive a greater ROI.

Let me explain why.

Machine Learning works out why certain outcomes happen based on past data. The output of the Machine Learning system is a model that can then predict the most likely outcome. Amazon Machine Learning is easy to use and with a few clicks in the web interface, builds predictive data-driven models. These Amazon built models can then be used to predict what will happen next based on new data.

Screenshot of the Amazon Machine Learning dashboard

Screenshot of the Amazon Machine Learning dashboard

Marketing use cases for Amazon Machine Learning

Let me give some examples:

Predicting which product/category/brand to lead with in an email campaign
Understanding what content is going to connect with customers will increase engagement and conversion. By modeling customer attributes and past product selections, you can make real-time decisions on what content to place in the email.

Selecting customers most likely to purchase a product
Machine learning can use past purchase data and customer attributes to build a model that can then be used to select which prospects are most likely to convert. This insight can be used to target prospects who are most likely to convert with high value marketing materials.

Determining when best to post certain content
Just like comedy, timing is crucial in marketing. Using past campaign and response data makes it possible for marketers to determine when to post certain content.

Calculating the likely response rate to certain campaigns
Campaign meta data and response rates can be modeled to determine how campaigns will perform in the future.

Go try it out

The element I’ve not covered in these examples is the combination of machine learning models to choose between multiple dimensions.

In my last post, I talked about omnichannel next best action. This new service from Amazon is crucial to pulling it off.

Amazon Machine Learning is a newly released platform from Amazon that models data from either a CSV file or a Amazon Redshift warehouse. Once created Amazon Machine Learning tests the model against a portion of the original data to determine how well it works.

The finished and tested model can then be used to produce batch decisions on a data set or alternatively used in real-time with your own applications. Certainly a nice addition to any Marketing Orchestration Platform.

If you’re unsure about Amazon Machine Learning, go try it out.

All you need is an AWS account and a CSV of some data. Follow the AWS Blog guide in the further reading section below to see how to get started. It really is simple.

Further reading:

Support the blog
If you could use it for your work, I recommend picking up a copy of the all channel Excel file for use in strategic decision making. At £99.

David Sealey is a trusted adviser to senior executives on getting the most from their investment in digital and data. David created Storm81 as a place to share his passion for business, digital technologies, multichannel marketing and everything else around these topics.

More about David Sealey

Follow me on Twitter
Connect with me on LinkedIn


Download the all marketing channels list
WEEKLY DIGITAL STRATEGY NEWSLETTER

follow us in feedly Follow on Feedly
Follow with RSS
A powerful and affordable survey software tool