---
title: "recommendations(fromUsers:maxCount:restrictingToItems:excluding:excludingObserved:)"
framework: createml
role: symbol
role_heading: Instance Method
path: "createml/mlrecommender/recommendations(fromusers:maxcount:restrictingtoitems:excluding:excludingobserved:)"
---

# recommendations(fromUsers:maxCount:restrictingToItems:excluding:excludingObserved:)

Retrieves the highest scored item for the given array of users, based on item similarity and the rating column.

## Declaration

```swift
func recommendations(fromUsers: [any MLIdentifier], maxCount: Int = 10, restrictingToItems: [any MLIdentifier]? = nil, excluding userItemObservations: MLDataTable? = nil, excludingObserved: Bool = true) throws -> MLDataTable
```

## Parameters

- `fromUsers`: An array of user identifiers.
- `maxCount`: The maximum number of recommendations per user. The default is 10.
- `restrictingToItems`: An array of item identifiers that defines the only values the recommender can use this set of recommendations. By default, the parameter is nil, meaning there are no restrictions.
- `userItemObservations`: A data table of user-item observations to exclude from recommendations. The default is nil, meaning no observations are excluded. The column names for the user identifiers and item identifiers must be the same as those provided in the training data.
- `excludingObserved`: Set this value to true to omit training data from the recommendations, or false to include them. The default is true.

## Return Value

Return Value An MLDataTable containing columns with user identifiers, item identifiers, scores and ranks (numbered between 1 and the maxCount).

## See Also

### Testing a recommender

- [MLIdentifier](createml/mlidentifier.md)
- [getSimilarItems(fromItems:maxCount:)](createml/mlrecommender/getsimilaritems(fromitems:maxcount:).md)