Skip to content

Commit 9e3805d

Browse files
applied feedback
1 parent e727eba commit 9e3805d

File tree

1 file changed

+3
-3
lines changed

1 file changed

+3
-3
lines changed

articles/cognitive-services/personalizer/concept-active-learning.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
title: Active and inactive events - Personalizer
33
titleSuffix: Azure Cognitive Services
4-
description:
4+
description: When your application calls the Rank API, you receive the action that the application should show in the **rewardActionId** field. From that moment, Personalizer expects a Reward call that has the same eventId. The reward score will be used to train the model for future Rank calls. If no Reward call is received for the eventId, a default reward is applied. Default rewards are set in the Azure portal.
55
services: cognitive-services
66
author: diberry
77
manager: nitinme
@@ -14,9 +14,9 @@ ms.author: diberry
1414

1515
# Active and inactive events
1616

17-
When your application calls the Rank API, you receive the action that the application should show in the **rewardActionId** field. From that moment, Personalizer expects a Reward call that has the same eventId. The reward score will be used to train the model for future Rank calls. If no Reward call is received for the eventId, a default reward is applied. Default rewards are set in the Azure portal.
17+
When your application calls the Rank API, you receive the action that the application should show in the **rewardActionId** field. From that moment, Personalizer expects a Reward call that has the same eventId. The reward score will be used to train the model for future Rank calls. If no Reward call is received for the eventId, a default reward is applied. Default rewards are set in the Azure portal.
1818

19-
In some scenarios, the application might call Rank bore even if it knows the result will be used or will be displayed to the user. These scenarios might happen when, for example, the page rendering of promoted content is overwritten by a marketing campaign. If the result of the Rank call was never used and the user never saw it, it would be incorrect to train it with any reward, whether zero or otherwise.
19+
In some scenarios, the application might call Rank before it even knows the result will be used or will be displayed to the user. These scenarios might happen when, for example, the page rendering of promoted content is overwritten by a marketing campaign. If the result of the Rank call was never used (displayed to the user), don't send a corresponding Reward call.
2020

2121
Typically, these scenarios happen when:
2222

0 commit comments

Comments
 (0)