# Prediction types and dataset requirements for models

*CRM Analytics and Einstein Discovery Consultant Study Guide · Einstein Discovery · Last updated November 3, 2026 · https://www.certifyforce.com/study-guide/crm-analytics-and-einstein-discovery-consultant/einstein-discovery/prediction-types-and-dataset-requirements-for-models*

Choosing the numeric, binary classification or multiclass classification use case from the outcome column, and shaping a dataset that meets Einstein Discovery's row, column, known-outcome and granularity requirements before you create a model.

- Certification: Salesforce CRM Analytics and Einstein Discovery Consultant
- Exam section: Einstein Discovery
- Study guide: https://www.certifyforce.com/study-guide/crm-analytics-and-einstein-discovery-consultant

**Official exam objective:**

> Build a model by assessing data and selecting one of the three types of predictions (numeric, binary, multi-classification).

## What the exam expects

- Pick the numeric, binary classification or multiclass classification use case from the outcome column's data type and number of values.
- Set the model goal correctly: Maximize or Minimize for numeric and binary outcomes, the most likely class for multiclass.
- Check a dataset against the minimums (rows with a known outcome, columns) and maximums before creating a model.
- Explain which rows Einstein Discovery trains on and why rows without an outcome drop out.
- Shape data from one or more sources into rows at the granularity the business question needs.

Key terms: **outcome variable** (the column the model predicts, set in **I Want to Analyze**); **explanatory variable** or predictor (a column that may influence the outcome); **observation** (one row of the dataset); **use case** (numeric, binary classification or multiclass classification, set by the outcome); **granularity** (what one row represents, such as a customer, a day or a shipment).

## Key facts

| Fact | Detail | Source |
|---|---|---|
| Three use cases | Numeric, binary classification, multiclass classification | [Define Your Target Outcome](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_plan.htm&type=5&language=en_US) |
| Multiclass range | Text outcome with 3-10 possible classes | [About Models](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_about.htm&type=5&language=en_US) |
| Maximize or Minimize | Numeric and binary outcomes only | [Configure Model](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_setup_start.htm&type=5&language=en_US) |
| Binary outcome data type | Text values; convert 1 and 0 to text | [Address Common Data Issues](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_prep_data_issues.htm&type=5&language=en_US) |
| Rows | 400 minimum with a known outcome, 20,000,000 maximum | [Capacities and Requirements](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_limits.htm&type=5&language=en_US) |
| Columns | 3 minimum (outcome plus 2), 50 maximum | [Capacities and Requirements](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_limits.htm&type=5&language=en_US) |
| Row with no outcome value | Omitted from analysis | [Determine Data Requirements](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_prep_requirements.htm&type=5&language=en_US) |
| Outcome list eligibility | Field needs values in at least 400 rows | [Configure Model](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_setup_start.htm&type=5&language=en_US) |
| Dataset with a predicate | Creator needs access to at least 400 rows | [Select a Dataset](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_setup_dataset.htm&type=5&language=en_US) |
| Not usable for models | Live datasets; multivalue fields | [Create a Model from a Dataset](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_create_dataset.htm&type=5&language=en_US), [Capacities and Requirements](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_limits.htm&type=5&language=en_US) |

## Check yourself

- Why might a text column you expect be missing from the I Want to Analyze list?
- When does a model pick up new rows added to its dataset after creation?
- Which algorithm family is offered for numeric and binary models but not multiclass?
- What does Show as whole number >= 0 do?
- When should a proof of concept limit its input variables?

## Sources

- [Define Your Target Outcome](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_plan.htm&type=5&language=en_US)
- [About Models](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_about.htm&type=5&language=en_US)
- [Determine Data Requirements](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_prep_requirements.htm&type=5&language=en_US)
- [Einstein Discovery Capacities and Requirements](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_limits.htm&type=5&language=en_US)
- [Configure Model](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_setup_start.htm&type=5&language=en_US)
- [Create a Model from a Dataset](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_create_dataset.htm&type=5&language=en_US)
- [Select a Dataset](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_setup_dataset.htm&type=5&language=en_US)
- [Considerations for Preparing Data](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_prep_considerations.htm&type=5&language=en_US)
- [Address Common Data Issues](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_prep_data_issues.htm&type=5&language=en_US)
- [Numerical Use Cases](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_about_use_case_numeric.htm&type=5&language=en_US)
- [Binary Classification Use Case](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_about_use_case_binary.htm&type=5&language=en_US)
- [Multiclass Classification Use Cases](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_about_use_case_multiclass.htm&type=5&language=en_US)

## About the full unit

The "Core concepts", "Exam traps" and "Worked scenario" sections of this unit, its 8 linked practice questions, and unlimited timed mock exams are included with the CRM Analytics and Einstein Discovery Consultant pack (USD $19): https://www.certifyforce.com/practice-exams