You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
<divclass="class-description">Recommends set of items that are somehow related to one given item, *X*. Typical scenario is when user *A* is viewing *X*. Then you may display items to the user that he might be also interested in. Recommend items to item request gives you Top-N such items, optionally taking the target user *A* into account.
34
-
It is also possible to use POST HTTP method (for example in case of very long ReQL filter) - query parameters then become body parameters.</div>
34
+
It is also possible to use POST HTTP method (for example in case of very long ReQL filter) - query parameters then become body parameters.
35
+
The returned items are sorted by relevancy (first item being the most relevant).</div>
35
36
36
37
37
38
</header>
@@ -189,9 +190,6 @@ <h5>Parameters:</h5>
189
190
190
191
<tdclass="description last">Optional parameters given as an object with structure name of the parameter: value
191
192
- Allowed parameters:
192
-
- *userImpact*
193
-
- Type: number
194
-
- Description: If *targetUserId* parameter is present, the recommendations are biased towards the user given. Using *userImpact*, you may control this bias. For an extreme case of `userImpact=0.0`, the interactions made by the user are not taken into account at all (with the exception of history-based blacklisting), for `userImpact=1.0`, you'll get user-based recommendation. The default value is `0`.
195
193
- *filter*
196
194
- Type: string
197
195
- Description: Boolean-returning [ReQL](https://docs.recombee.com/reql.html) expression which allows you to filter recommended items based on the values of their attributes.
@@ -204,6 +202,11 @@ <h5>Parameters:</h5>
204
202
- *scenario*
205
203
- Type: string
206
204
- Description: Scenario defines a particular application of recommendations. It can be for example "homepage", "cart" or "emailing". You can see each scenario in the UI separately, so you can check how well each application performs. The AI which optimizes models in order to get the best results may optimize different scenarios separately, or even use different models in each of the scenarios.
205
+
- *logic*
206
+
- Type: string|
207
+
- Description: Logic specifies particular behavior of the recommendation models. You can pick tailored logic for your domain (e-commerce, multimedia, fashion ...) and use case.
208
+
See [this section](https://docs.recombee.com/recommendation_logic.html) for list of available logics and other details.
209
+
The difference between `logic` and `scenario` is that `logic` specifies mainly behavior, while `scenario` specifies the place where recommendations are shown to the users.
207
210
- *returnProperties*
208
211
- Type: boolean
209
212
- Description: With `returnProperties=true`, property values of the recommended items are returned along with their IDs in a JSON dictionary. The acquired property values can be used for easy displaying of the recommended items to the user.
@@ -260,6 +263,9 @@ <h5>Parameters:</h5>
260
263
]
261
264
}
262
265
```
266
+
- *userImpact*
267
+
- Type: number
268
+
- Description: **Expert option** If *targetUserId* parameter is present, the recommendations are biased towards the given user. Using *userImpact*, you may control this bias. For an extreme case of `userImpact=0.0`, the interactions made by the user are not taken into account at all (with the exception of history-based blacklisting), for `userImpact=1.0`, you'll get user-based recommendation. The default value is `0`.
263
269
- *diversity*
264
270
- Type: number
265
271
- Description: **Expert option** Real number from [0.0, 1.0] which determines how much mutually dissimilar should the recommended items be. The default value is 0.0, i.e., no diversification. Value 1.0 means maximal diversification.
@@ -274,7 +280,10 @@ <h5>Parameters:</h5>
274
280
- Description: **Expert option** If the *targetUserId* is provided: Taking *rotationRate* into account, specifies how long time it takes to an item to recover from the penalization. For example, `rotationTime=7200.0` means that items recommended less than 2 hours ago are penalized.
275
281
- *expertSettings*
276
282
- Type:
277
-
- Description: Dictionary of custom options.</td>
283
+
- Description: Dictionary of custom options.
284
+
- *returnAbGroup*
285
+
- Type: boolean
286
+
- Description: If there is a custom AB-testing running, return name of group to which the request belongs.</td>
<divclass="class-description">Based on user's past interactions (purchases, ratings, etc.) with the items, recommends top-N items that are most likely to be of high value for a given user.
34
-
It is also possible to use POST HTTP method (for example in case of very long ReQL filter) - query parameters then become body parameters.</div>
34
+
It is also possible to use POST HTTP method (for example in case of very long ReQL filter) - query parameters then become body parameters.
35
+
The returned items are sorted by relevancy (first item being the most relevant).</div>
35
36
36
37
37
38
</header>
@@ -166,6 +167,11 @@ <h5>Parameters:</h5>
166
167
- *scenario*
167
168
- Type: string
168
169
- Description: Scenario defines a particular application of recommendations. It can be for example "homepage", "cart" or "emailing". You can see each scenario in the UI separately, so you can check how well each application performs. The AI which optimizes models in order to get the best results may optimize different scenarios separately, or even use different models in each of the scenarios.
170
+
- *logic*
171
+
- Type: string|
172
+
- Description: Logic specifies particular behavior of the recommendation models. You can pick tailored logic for your domain (e-commerce, multimedia, fashion ...) and use case.
173
+
See [this section](https://docs.recombee.com/recommendation_logic.html) for list of available logics and other details.
174
+
The difference between `logic` and `scenario` is that `logic` specifies mainly behavior, while `scenario` specifies the place where recommendations are shown to the users.
169
175
- *returnProperties*
170
176
- Type: boolean
171
177
- Description: With `returnProperties=true`, property values of the recommended items are returned along with their IDs in a JSON dictionary. The acquired property values can be used for easy displaying of the recommended items to the user.
@@ -236,7 +242,10 @@ <h5>Parameters:</h5>
236
242
- Description: **Expert option** Taking *rotationRate* into account, specifies how long time it takes to an item to recover from the penalization. For example, `rotationTime=7200.0` means that items recommended less than 2 hours ago are penalized. Default: `7200.0`.
237
243
- *expertSettings*
238
244
- Type:
239
-
- Description: Dictionary of custom options.</td>
245
+
- Description: Dictionary of custom options.
246
+
- *returnAbGroup*
247
+
- Type: boolean
248
+
- Description: If there is a custom AB-testing running, return name of group to which the request belongs.</td>
<divclass="class-description">Recommend users that are likely to be interested in a given item.
34
-
It is also possible to use POST HTTP method (for example in case of very long ReQL filter) - query parameters then become body parameters.</div>
34
+
It is also possible to use POST HTTP method (for example in case of very long ReQL filter) - query parameters then become body parameters.
35
+
The returned users are sorted by predicted interest in the item (first user being the most interested).</div>
35
36
36
37
37
38
</header>
@@ -166,6 +167,11 @@ <h5>Parameters:</h5>
166
167
- *scenario*
167
168
- Type: string
168
169
- Description: Scenario defines a particular application of recommendations. It can be for example "homepage", "cart" or "emailing". You can see each scenario in the UI separately, so you can check how well each application performs. The AI which optimizes models in order to get the best results may optimize different scenarios separately, or even use different models in each of the scenarios.
170
+
- *logic*
171
+
- Type: string|
172
+
- Description: Logic specifies particular behavior of the recommendation models. You can pick tailored logic for your domain (e-commerce, multimedia, fashion ...) and use case.
173
+
See [this section](https://docs.recombee.com/recommendation_logic.html) for list of available logics and other details.
174
+
The difference between `logic` and `scenario` is that `logic` specifies mainly behavior, while `scenario` specifies the place where recommendations are shown to the users.
169
175
- *returnProperties*
170
176
- Type: boolean
171
177
- Description: With `returnProperties=true`, property values of the recommended users are returned along with their IDs in a JSON dictionary. The acquired property values can be used for easy displaying the recommended users.
@@ -221,7 +227,10 @@ <h5>Parameters:</h5>
221
227
- Description: **Expert option** Real number from [0.0, 1.0] which determines how much mutually dissimilar should the recommended items be. The default value is 0.0, i.e., no diversification. Value 1.0 means maximal diversification.
222
228
- *expertSettings*
223
229
- Type:
224
-
- Description: Dictionary of custom options.</td>
230
+
- Description: Dictionary of custom options.
231
+
- *returnAbGroup*
232
+
- Type: boolean
233
+
- Description: If there is a custom AB-testing running, return name of group to which the request belongs.</td>
0 commit comments