Jagmeet Kaur Author's Perspective
4 Minute read

How Cortex and Azure ML work together to drive personalization

How Cortex and Azure ML drive personalization

Personalization as well as machine learning are touching the higher grounds these days. Every company/brand is investing a large amount of their money on these to increase their revenue exponentially. Some of the giant multinational companies like Amazon, Facebook, Spotify, Netflix, etc. are making use of personalization and machine learning to increase customer engagement on their websites. 


“If we have 4.5 million customers,
we shouldn’t have one store.
We should have 4.5 million stores,”

- Jeff Bezos

98% of customer have disengaged
from brands when they don’t
get a personalized experience

58% of customer have said
that personalization is an important
factor in determining purchase

So what exactly is Personalization? And how to achieve this? Personalization is the method by which we show relevant content to the customers based on their needs, demands and their individual preferences, rather than showing the same content to every visitor on the website. Personalization helps to make customers happy (satisfied) by focusing on everyone's individuality and to make sure that the right content reaches the right audience at the right time.

In Sitecore, we perform personalization by setting up rules and pattern cards to show, hide and adjust content based on the location, gender, or previous pages visited on the site.

To accomplish personalization using Sitecore, we have to set up rules manually and need a dedicated resource to perform such tasks. A lot of money and time is spent on the resources and software setup for this, even after spending such a large amount of money, it is very easy to miss the mark with these manual methods. 

Some of the shortcomings of rule-based personalization are given below:

• It is very complex to develop and write rules and set persona for every individual visiting the site. 

• With the use of manual methods of personalization, it is easy to miss the mark 

• In today's world, requirements and needs of users change every now and then, and manual personalization won't perform dynamically.

• Even the most experienced and expert individual sometimes miss the minor details of something and can only identify the high-level segments only.

•New patterns, groupings, segments, and subconscious behaviors will remain undiscovered with rule-based personalization

• It is very expensive to hire experts to incur such needs.

But bringing machine learning into personalization can address most of these challenges. In this blog, we will be discussing what is machine learning? Flow of any machine learning algorithm? How machine learning can be used for personalizing?

What is Machine Learning?

Machine Learning provides us with the methods and algorithms that can predict and return the output with the help of some input or a set of values as input without being explicitly programmed. Like we respond to any situation based on our needs and past experience about anything, in the same way, machine learning helps to predict the response and relevance of something based on them based on the past experience that is extracted from the data fed to the machine learning algorithms. Machine Learning is the most scalable means to perform personalization and helps to represent the much-needed content dynamically to the customers. 

Why isn’t everyone doing ML-based Personalization?

People do not know where to start and what to do in order to achieve the outcome in the best possible manner. Even if they are able to they are able to start and develop ML algorithms, they do not know how to maintain it.

Websites are generating an enormous amount of data on a daily basis and it is not possible for beginner or intermediate to make use of such a huge exponentially increasing data to perform dynamically.

 Following are the basic steps for any machine learning algorithm:

Our Approach:

In this demo, we have used azure machine learning studio for performing machine learning tasks and the Sitecore cortex for content tagging part. 

The following figure broadly describes different machine learning and artificial intelligence components. Artificial intelligence consists of machine learning, reasoning, NLP and planning. Machine learning further divided into supervised, unsupervised, reinforcement and deep learning. In the demo, we are using NLP, Supervised, unsupervised machine learning algorithms.


Webinar On-Demand

1-1 Personalisation using Azure ML and Sitecore: A step towards better user experience

Following are modules that are developed in this demo:

• Sitecore Cortex (Content Tagging) 

• Data Enrichment

• Data segmentation

• Training and Prediction

• Custom Personalization Rules 

Sitecore Cortex (Content Tagging): From version 9.1, Sitecore provides the capability to tag the items by clicking on the 'Tag Item' button available in the ribbon (screenshot below). 

The Sitecore cortex content tagging make use of third party API-Open Calais. But somehow open Calais was not working as our requirements. So, we overrode Retrieve Content Pipeline and Get Tags Pipeline and developed our own NLP model using Azure ML studio. Following is the flow of step to develop NLP algorithm.

Clustering and Prediction:

  1. Data gathering: We have used XDb interaction data and the tagging data associated with each and every item obtained from the previous step. 
  2. Data enrichment: We have the raw XDb interaction data and Sitecore item tags data. in order to get the best results by applying the machine learning algorithms, there is the need to convert this raw noisy and untidy data to some enriched form that can be fed to models because output is directly proportional to the quality and quantity of the data. we have Preprocessed raw data, treated missing values, removed highly correlated items transform and categorize and used One hot encoding techniques for data enrichment.
  3. Data Segmentation: In this step, we have segmented the preprocessed data by extracting the relevant features using feature selection and then applying sweep clustering and Kmeans clustering.
  4. Training: after obtaining the clustered data from the previous step, we have divided the data into two samples training and testing and performed model building and model tuning techniques iteratively to get the best model.
  5. Prediction and Recommendation: The model that is built in the previous step is able to predict the most accurate segment/cluster to which any interaction or behavior of visitor belongs to. Then in order to perform the recommendation task, we have integrated another algorithm which was developed based on the principles of market-basket analysis.

Summary of steps:

Architecture diagram:

Why should we use AzureML studio for machine learning tasks? 

• Build for cloud-first mobile-first world 

• Reduced Complexity 

• Collaborate work with anyone 

• Visual composition, easy to use, drag and drop

 • 500 + Inbuilt R Packages / Python Anaconda toolkit

 • Standard ML algorithms & tools (Text mining, Regression, 

• Classification, Clustering, Anomaly detection)

 • Data sources (Azure Blob, RDBMS, Hive, Web) 

• Data preparation (preprocessing, aggregation, transformation, feature engineering) 

• Deploy in minutes

Altudo is a Sitecore Platinum partner with 500+ Sitecore projects delivered for 45+ Fortune 500 brands, across 7 industry verticals
We help you realize the true potential of your marketing efforts, speeding up the Time to Value by leveraging CX strategy, 1:1 personalization & our global delivery expertise.

Jagmeet Kaur
Jagmeet Kaur Senior Associate

Talk to our Experts

Talk to us about how we bring together 1:1 personalisation, deep Martech Expertise, CX & Demand Gen Strategy, Engagement Analytics & Cross-Channel Orchestration to drive award winning experiences that convert

Get in touch for a complimentary consultation or a demo today.

Expert Workshops

Free workshops, expert advice & demos- to help your realize value with Sitecore


Session Presentations

  • Sitecore + SFMC= Marketing Success
  • Transforming The Future Of eCommerce
Meet Us


Participate in our event survey , meet us at our booth , get free giveaways & a chance to win an iPhone 11

Let’s go
Close Button