Einstein Prediction Builder

Einstein Studio has an Add Predictive Model action which allows you to either connect to an external predictive model, or to create a model from scratch. When you choose to create a model from scratch, you are led through the configuration of a predictive model with essentially the same features as have previously existed in Einstein Prediction Builder. The major difference is that all of the data sources for training and test data, as well as data sources when you're ready to make inferences, are the Data Cloud DMOs.

The Einstein Prediction Builder feature which has been in the platform for several years will probably continue to exist for customers who have no interest in using Data Cloud,  and have good data management practices within Salesforce Core. But it is inherently more limited due to its needing to work with data within the legacy Salesforce object storage. My own prediction is that we will see the Einstein Model Builder take on a greater diversity of data science use cases and product evolution in years to come, and that the Einstein Prediction Builder will always be limited to its current feature set of regression and classification only.

Hello

1. Regarding the length of the prediction, if you're using Einstein Prediction Builder to create the prediction, you can't directly control the length of the predicted value. However, you can manipulate the predicted value using formulas in Salesforce. For example, if your prediction is a decimal number between 1 and 10, you can use a formula field to round the prediction to a certain number of decimal places or convert it into a whole number. This can help shorten the length of the prediction. Alternatively, you can use Apex triggers or processes to manipulate the prediction value after it's generated by Einstein Prediction Builder.
2. If you're using Einstein Discovery, users without a license won't be able to directly interact with the Einstein Discovery component on the Account page. Access to Einstein Discovery features typically requires a Salesforce Einstein Analytics Plus license. However, you can still use the predictions generated by Einstein Discovery in your Salesforce processes, such as workflows, validation rules, or Apex triggers, to automate actions or decisions based on the predictions. This way, users without a license can indirectly benefit from the predictions through the automated actions triggered by them.

Einstien opp scores use the following objects:

Account, Contact, CurrencyType, Event, EventRelation, Lead, Opportunity, OpportunityContactRole, OpportunityFieldHistory, OpportunityHistory, OpportunityLineItem, OpportunityScore, OpptyScoringAIApplicationConfig, OpportunityStage, OpportunityTeamMember, PIAIApplicationConfig, PricebookEntry, Quote, RecordType, SalesAIScoreCycle, SalesAIScoreModelFactor, TaskOrganization, PermissionSet, PermissionSetAssignment, PermissionSetLicense, PermissionSetLicenseAssign, User, UserRole, Profile, OrgWideEmailAddress, MLModel, AIRecordInsight, AIInsightValue, AIInsightReason, SalesAIScoreCycle, SalesAIScoreAIFactor, AIApplication, MLPredictionDefinition, VoiceCall, VideoCall, VideoCallParticipant, OpportunitySplitType, OpportunitySplit objects, Product2, Product2History, Enterprise Territory Management objects, OpportunityLineItemSchedule, QuoteLineItem, Quote, Order, OrderItem, Contract, ContractLineItem, Invoice, InvoiceLine, Asset, AssetTag, Product2, ProductMedia.

If Einstein Activity Capture is enabled: User emails, email insights, meeting data (events).

If Einstein Conversation Insights is enabled: Insights.

Source: https://help.salesforce.com/s/articleView?id=sf.admin_einstein_features_data_usage.htm&type=5