Are non-categorical fields used for training in Amazon Personalize with User Personalization recipe?

Question

For example, if I have the following User schema:

```
{
	"name": "USER_ID",
	"type": "string"
},
{
	"name": "AGE",
	"type": [
	  "null",
	  "int"
	],
        "categorical": true
},
{
	"name": "GENDER",
	"type": [
          "null",
	  "string"
	],
},
{
        "name": "USER_DESCRIPTION",
        "type": "string"
}
```

Will the "GENDER" field be used for training or will only the "AGE" be used for training?

Also, what are the differences between contextual & categorial metadata?

Is this applicable for Users, Item, and User-Item interactions?

I am new to Amazon Personalize, so I apologize if this is trivial.

Answer

Hi & thanks for asking!

As mentioned in the "Metadata fields" section of the [Custom Datasets and Schemas](https://docs.aws.amazon.com/personalize/latest/dg/custom-datasets-and-schemas.html) developer guide page:

> If you add your own metadata field of type string, it must include the `categorical` attribute or the `textual` attribute (only Items schemas support fields with the textual attribute). Otherwise, Amazon Personalize won't use the field when training a model.

...So you must explicitly specify string fields as either categorical or textual, otherwise Personalize will ignore them in model training (which can also be useful - if you'd like to include a field for filtering purpose but not have it affect the model). Since you're building a user metadata schema, not item - it'll need to be categorical.

However - I think you'll also need to remove the `categorical` flag from your "AGE" field there: since it's a numeric rather than string. You can also refer to [this example user metadata schema](https://docs.aws.amazon.com/personalize/latest/dg/user-dataset-requirements.html#schema-examples-users).

Are non-categorical fields used for training in Amazon Personalize with User Personalization recipe?

Relevant content