Ranking
Ranking models are often used in recommendation systems, ads, search engines, etc. In Aporia, these models are represented with the
ranking
model type.If you have a ranking or recommendations model, then your database may look like the following:
id | feature1 (numeric) | feature2 (boolean) | Ordered Recommandations(array) | Actual (array) | timestamp (datetime) |
---|---|---|---|---|---|
1 | 13.5 | True | [item1, item2, ...] | [item3, item4] | 2014-10-19 10:23:54 |
2 | -8 | False | [item3, item2, ...] | [item3] | 2014-10-19 10:24:24 |
To integrate this type of model follow our Quickstart, and during the schema mapping remember to include a
array
prediction field and array
actual field and linked them together.Notice the recommendation array (prediction) should be ordered by the query that defines the Dataset
Check out the data sources section for more information about how to connect from different data sources.
Last modified 4mo ago