web
You’re offline. This is a read only version of the page.
close
Skip to main content

Notifications

Announcements

No record found.

News and Announcements icon
Community site session details

Community site session details

Session Id :
Dynamics 365 Community / Forums / Customer experience | Sales, Customer Insights,... / customer insights data...
Customer experience | Sales, Customer Insights,...
Unanswered

customer insights data predictions

(1) ShareShare
ReportReport
Posted on by devpurpose 6
hello everyone,i'm following this guide Product recommendation prediction sample guide - Dynamics 365 Customer Insights | Microsoft Learn . I did all steps but i receive an error on creating the model for predictions.
Someone can help me please?
The errors are:
customer profile intelligence -> Dependencies upstream of the requested component have been skipped
data preparation -> The dependencies 'OOB Product Recommendation Model Prediction (ModelManagement)' of this process were failed. Please make sure the failed dependencies are refreshed successfully and try again.
 
ErrorMore data's needed to generate predictions. Try adding more to your data table, then run the model again. DetailedError: 'Number of missing values in column TransactionID is too many.'
ErrorMore data's needed to generate predictions. Try adding more to your data table, then run the model again. DetailedError: 'Number of missing values in column ProductID is too many.'
Warning100% of customers in your data have less than 3 purchases. To improve the model performance it is recommended that you add more data, if available, to increase the number of purchases per customer.
WarningYour input data seems to be missing the last 57.029292438271604 months of data. Consider adding data for these months to get more relevant recommendations.
 
 
 
I have the same question (0)
  • Dengliang Li Profile Picture
    Dengliang Li Microsoft Employee on at
    Hi,
     
    I encountered the same issue as you in my testing.
    According to the official documentation, this is a preview feature. The preview feature is not complete.
    If you are using an existing environment, it is recommended that you try this prediction in a new environment.

    Best Regards,
    Dengliang Li
     
  • Joy Taylor Profile Picture
    Joy Taylor on at
    This seems to be a problem with the data used. There are too many data gaps to create a prediction.  Is there any way you can possibly fill the information gaps or add any additional older data? 
  • sebedb Profile Picture
    sebedb 16 on at
    Same here, its a shame whoever created it doesnt seem to care, no wonder people are gravitating towards Salesforce and Trailhead with these repeating negative experiences with microsoft learn,  i reported the tutorial

Under review

Thank you for your reply! To ensure a great experience for everyone, your content is awaiting approval by our Community Managers. Please check back later.

Helpful resources

Quick Links

Responsible AI policies

As AI tools become more common, we’re introducing a Responsible AI Use…

Neeraj Kumar – Community Spotlight

We are honored to recognize Neeraj Kumar as our Community Spotlight honoree for…

Congratulations to the November Top 10 Community Leaders!

These are the community rock stars!

Leaderboard > Customer experience | Sales, Customer Insights, CRM

#1
Tom_Gioielli Profile Picture

Tom_Gioielli 70 Super User 2025 Season 2

#2
Gerardo Rentería García Profile Picture

Gerardo Rentería Ga... 33 Most Valuable Professional

#3
Daniyal Khaleel Profile Picture

Daniyal Khaleel 32 Most Valuable Professional

Last 30 days Overall leaderboard

Featured topics

Hide selecting Contact for potential customer when creating quote

Product updates

Dynamics 365 release plans