Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update blacklistEvents to blacklistIndicators #18

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update blacklistEvents to blacklistIndicators #18

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions h_ur_advanced_tuning.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,11 +46,11 @@ If training and query times are not a factor these can safely be increased with

The default `blacklistIndicators` in the engine parameters is the single primary event. This means that if the user took the primary event on an item it will not be returned in recommendations. This is often the right thing to do but there are exceptions.

In some cases an item may be consumed periodically like Clothing, or Food so reminding a user that they like an item may be good. To disable the blacklist set the following `"blacklistEvents": []`, which means to return all recommendations without restriction.
In some cases an item may be consumed periodically like Clothing, or Food so reminding a user that they like an item may be good. To disable the blacklist set the following `"blacklistIndicators": []`, which means to return all recommendations without restriction.

It is possible with this setting to get only things the user is already familiar with. Disabling the blacklist may not be the best way to handle this. For instance lets say you have 10 recommendations to show; it might be better to get 9 recommendations (with the blacklist) and put in one item you already know the user prefers from your own data. Any mixing of items the user is familiar with and recommendations can be done as part of the application logic, not implemented by the recommender.

In other cases you may want to be more restrictive and use more than the primary event to filter out items from recs. Setting to `"blacklistEvents": ["buy", "view"]` is a good example, where anything the use bought or any item detail page the user viewed will will result in those items not being returned as recommendations.
In other cases you may want to be more restrictive and use more than the primary event to filter out items from recs. Setting to `"blacklistIndicators": ["buy", "view"]` is a good example, where anything the use bought or any item detail page the user viewed will will result in those items not being returned as recommendations.

## Anti Flood

Expand Down
4 changes: 2 additions & 2 deletions h_ur_config.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,7 +95,7 @@ How to read config settings:
},
...
],
"blacklistEvents": ["<list>", "<of>", "<indicator>", "<names>"],
"blacklistIndicators": ["<list>", "<of>", "<indicator>", "<names>"],
"maxEventsPerEventType": <some-int>,
"maxCorrelatorsPerEventType": "<some-int>",
"maxQueryEvents": <some-int>,
Expand Down Expand Up @@ -167,7 +167,7 @@ How to read config settings:
},
...
],
"blacklistEvents": ["primary-indicator-name"], // OPTIONAL
"blacklistIndicators": ["primary-indicator-name"], // OPTIONAL
"maxEventsPerEventType": 500, // OPTIONAL
"maxCorrelatorsPerEventType": 50, // OPTIONAL
"maxQueryEvents": 100, // OPTIONAL
Expand Down