Interaction Studio SFMC Personalization

Hii 

  Vinícius,

Changing identity merge settings in Marketing Cloud Personalization needs careful planning. Here is what the documentation says: 

• After you create an identity type, you can't edit or delete it. salesforce
• Salesforce says to set up the identity system during implementation, before you collect any data in your production dataset. If you already collect data, the Trailhead module says there are additional considerations, and it points to the "Create an Identity Type" and "User Identity Mapping" articles. salesforceSalesforce
• When profiles are merged, only identity types with the Identity Namespace uniqueness value are considered. A "Not Unique" value can't be used for lookup or merging. salesforce
• When a profile merge happens, older profiles are merged into the most recently updated one. If the same attribute exists on more than one profile, the value with the latest timestamp is kept. Salesforce
• If you change the WebSDK identity attribute, your sitemap must send that ID as the user ID. Open Time Email supports only one identity as its match key. Salesforce

So before you change anything, list which identity types and channels (web, ETL, email) use them today, and confirm the change with Salesforce Support. Which change are you planning: the WebSDK identity, a new identity type, uniqueness, or case sensitivity? 

Referenced link: 

 https://help.salesforce.com/s/articleView?id=mktg.mc_pers_identity_type_create.htm&type=5 

https://trailhead.salesforce.com/content/learn/modules/identity-system-in-marketing-cloud-personalization/configure-the-identity-system 

Hi Micheala, 

What you’re seeing can be consistent with how Einstein Decisions balances exploration and exploitation. A promotion that initially performs better can receive a larger share of traffic as the model gains confidence, so equal eligibility does not necessarily mean equal impression distribution. 

I’d monitor the Einstein Decisions Report over multiple training cycles rather than judging the model from the first 24 hours. In particular, look at impressions, clicks/CTR, exploration vs. exploitation behavior, and how the model’s preference changes over time. 

For the five deactivated promotions, I’d verify the training-data behavior in the Einstein Decisions documentation for your specific MCP configuration. Historical data can be relevant to model training, but the exact retention and influence period is something I wouldn’t assume without confirming the current product documentation. 

If the distribution remains heavily skewed while the performance data does not support the preference, then I’d investigate eligibility, content-zone configuration, audience/context attributes, and campaign setup before concluding that the model is behaving incorrectly. 

Your approach of letting the model collect more data while monitoring the training reports sounds reasonable. If you can share the specific Einstein Decisions Report metrics from the first few training cycles, the community may be able to help determine whether the behavior looks expected.

You need to pull those attributes in the serverside.ts part of your Template with context.user.attributes.attributeName (for example, within return statement of run(context: CampaignComponentContext) so that it is visible in the payload. 

Only then you will be able to leverage that in the frontend handlebars.hbs section by referencing the payload passed from TS.

Example: https://github.com/evergage/evergage-global-templates/blob/master/infobar-with-user-attribute-and-cta/template.ts

@Interaction Studio SFMC Personalization

Are you referring to marketing cloud personalization (formerly Interaction Studio) or email recommendations? 

If it's marketing cloud personalization, it's possible to create a segment based on the time a user spent viewing a product. 

You can verify this at this link:

Hi @Dinesh Kumavat

, my guess is that the issue you are running may be related to the the timing of when the different code elements are loaded into the page.  From my understanding, the MCP web campaigns (templates) are loaded onto the page by the Beacon script so it could be that the form you want the reCAPTCHA to validate just isn't there yet at the time it is looking for it.  I would recommend trying to troubleshoot by looking at the timing around how both scripts are loaded and see if there is a way to time the reCAPTCHA code only after the MCP form is loaded.  

I hope this helps.

The answer would depend on the type of personalization logic and types you need to drive and future platform strategy.  

One option is MCP as you mentioned and in this case that is a powerful platform for real time Personalization with built-in engagement tracking and segmentation solution. The con - it’s is only maintained, not expanded by Salesforce. 

As you already have Data Cloud, a better option might be to check the new Salesforce Personalization tool, that is successor to MCP built on the Data Cloud and very actively developed. It’s not yet as powerful as MCP, but will let you leverage your current implementation, integrate better into Salesforce CRM, be much more future proof and should deliver standard Personalization use cases without issue. 

I would check whether Salesforce Personalization can cover your use cases and how would the cost of Data Cloud + Salesforce Personalization (usage-based pricing) stack against Marketing Cloud Personalization (licence-based pricing), factor in future-proofing and potential expansions into Agentforce, and go from there with decision.