Marketing Cloud Release Notes | Interaction Studio
Interaction Studio: Now Powered by Einstein
Salesforce has made it effortless to visualize, track, and manage customer experiences with real-time interaction management, and now it is powered by Einstein also. Check out these latest Salesforce Marketing Cloud Release Notes of Interaction Studio
Improve product recommendations: The interaction studio is now powered by Einstein. With salesforce’s acquisition of evergage the leading AI-powered personalization engine, We now have machine learning baked right into interaction studios to power one-to-one customer experiences. There are two main methods to achieve personalization at the individual level the first method is through the use of customizable algorithms called Einstein personalization recipes which make it easier than ever to recommend content, products, categories, brands, and more. With recipes, non-technical business users can build, manage, test, and implement AI-powered recommendation strategies with results determined and delivered in real-time.
Personalize in real-time: The second method for delivering one-to-one personalization is by using Einstein personalization decisions which use an advanced algorithm called contextual bandit to decide and deliver the next best offer action or experience that decision takes into account both the likelihood of someone engaging with a particular action as well as the business value to the company.
Engage using AI: This is going to be a quick walk through how you can leverage Einstein personalization recipes into personalization decisions to power one-to-one machine learning-driven experiences across channels. Where we’ll start with Einstein personalization recipes.
Watch this video for more detailed information:
Optimize engagement: What we’re going to do is walk through the different components that you’re able to configure as that business user to set up your recommendation strategy so, for this case, we’ll be walking through a product recommendation strategy where you can see that we’ve leveraged an approach of blending two different algorithms together from our out of the box algorithms that are available within that drop-down list.
From there we can then layer in inclusions or exclusions to further refine
what is actually eligible to be recommended to that end user by the machine learning approach.
Then even layer in boosters based on the rich breadth and depth of data that we have about that individual prospect or customer in their unified customer profile to further enhance how we’re going to be thinking about that person as that individual shopper or customer.
Finally to make sure that we’re not going to be recommending a single product or a single product type or category too much we can layer in variations whether that’s randomized or dimensional to limit what can actually be shown to that person.
From there you’re able to actually test or preview how that recommendation strategy might behave within that recipe simulator as that final gut check before publishing it for use across your channels or campaigns
Beyond just product recommendations, we’re also able to actually promote content blogs, articles, or categories which really helps apply this recommendation strategy or approach to a number of different verticals as you think about the types of things that you’re actually able to recommend to that end-user once you’ve created the recommendation strategies you can then understand how they’re actually performing
You can A/B test them against each other
and even understand what products or content are being shown to that end user by that machine learning algorithm.
We can also leverage machine learning through the Einstein personalization decisions to the power that next best offer or promotion by understanding all the different promotions and offers and their associated validity and eligibility criteria
We can take all of the rich data we have about that individual customer. pair it up with that deep contextual data as well as various things like propensity scores that your data science team might be developing to think about out of all those offers that they might be eligible for, what are that offer or promotion that has both the highest likelihood of engagement and highest value to the business to then make sure that regardless of what channel or interaction point we’re providing one-to-one machine learning across every facet of that customer experience.
In this blog post we try to cover every update of Marketing Cloud Release Notes of Interaction Studio, Let us know If you have any doubts regarding this in the comment section.
Check out some additional Salesforce Marketing Cloud Release Notes here:
- Salesforce Marketing Cloud Release Notes Highlights
- Salesforce Marketing Cloud Release Notes | Distributed Marketing
- Salesforce Marketing Cloud Release Notes | Journey Builder
- Salesforce Marketing Cloud Release Notes | Einstein
- Multi-Factor Authentication
- Datorama: Ecommerce Optimizer
- Interaction Studio Powered by Einstein
- Journey Builder: Behavioral Triggers
- Marketing Cloud Release Notes
- July 2020 Release
- Marketing Cloud App and Setup July 2020 Release Notes
- Marketing Cloud Cross-Cloud Integrations July 2020 Release Notes
- Marketing Cloud Data Management July 2020 Release Notes
- Marketing Cloud Einstein July 2020 Release Notes
- Marketing Cloud Journeys and Messages July 2020 Release Notes
- Release Note announcement Registration