Recombee API Client
Public Member Functions | Properties | List of all members
Recombee.ApiClient.ApiRequests.RecommendItemsToItem Class Reference

Recommend items to item More...

Inheritance diagram for Recombee.ApiClient.ApiRequests.RecommendItemsToItem:
Inheritance graph
[legend]
Collaboration diagram for Recombee.ApiClient.ApiRequests.RecommendItemsToItem:
Collaboration graph
[legend]

Public Member Functions

 RecommendItemsToItem (string itemId, string targetUserId, long count, string scenario=null, bool? cascadeCreate=null, bool? returnProperties=null, string[] includedProperties=null, string filter=null, string booster=null, Logic logic=null, double? userImpact=null, double? diversity=null, string minRelevance=null, double? rotationRate=null, double? rotationTime=null, Dictionary< string, object > expertSettings=null, bool? returnAbGroup=null)
 Construct the request More...
 
override string Path ()
 
Returns
URI to the endpoint including path parameters
More...
 
override Dictionary< string, object > QueryParameters ()
 Get query parameters More...
 
override Dictionary< string, object > BodyParameters ()
 Get body parameters More...
 
- Public Member Functions inherited from Recombee.ApiClient.ApiRequests.Request
 Request (HttpMethod httpMethod, int timeoutMilliseconds, bool ensureHttps=false)
 Construct the request More...
 

Properties

string ItemId [get]
 ID of the item for which the recommendations are to be generated. More...
 
string TargetUserId [get]
 ID of the user who will see the recommendations. Specifying the targetUserId is beneficial because: More...
 
long Count [get]
 Number of items to be recommended (N for the top-N recommendation). More...
 
string Scenario [get]
 Scenario defines a particular application of recommendations. It can be for example "homepage", "cart" or "emailing". You can set various settings to the scenario in the Admin UI. You can also see performance of each scenario in the Admin 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. More...
 
bool? CascadeCreate [get]
 If item of given itemId or user of given targetUserId doesn't exist in the database, it creates the missing entity/entities and returns some (non-personalized) recommendations. This allows for example rotations in the following recommendations for the user of given targetUserId, as the user will be already known to the system. More...
 
bool? ReturnProperties [get]
 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. Example response: More...
 
string[] IncludedProperties [get]
 Allows to specify, which properties should be returned when returnProperties=true is set. The properties are given as a comma-separated list. Example response for includedProperties=description,price: More...
 
string Filter [get]
 Boolean-returning ReQL expression which allows you to filter recommended items based on the values of their attributes. Filters can be also assigned to a scenario in the Admin UI. More...
 
string Booster [get]
 Number-returning ReQL expression which allows you to boost recommendation rate of some items based on the values of their attributes. Boosters can be also assigned to a scenario in the Admin UI. More...
 
Logic Logic [get]
 Logic specifies particular behavior of the recommendation models. You can pick tailored logic for your domain and use case. See this section for list of available logics and other details. The difference between logic and scenario is that logic specifies mainly behavior, while scenario specifies the place where recommendations are shown to the users. Logic can be also set to a scenario in the Admin UI. More...
 
double? UserImpact [get]
 **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. More...
 
double? Diversity [get]
 **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. More...
 
string MinRelevance [get]
 **Expert option** If the targetUserId is provided: Specifies the threshold of how much relevant must the recommended items be to the user. Possible values one of: "low", "medium", "high". The default value is "low", meaning that the system attempts to recommend number of items equal to count at any cost. If there are not enough data (such as interactions or item properties), this may even lead to bestseller-based recommendations to be appended to reach the full count. This behavior may be suppressed by using "medium" or "high" values. In such case, the system only recommends items of at least the requested relevance, and may return less than count items when there is not enough data to fulfill it. More...
 
double? RotationRate [get]
 **Expert option** If the targetUserId is provided: If your users browse the system in real-time, it may easily happen that you wish to offer them recommendations multiple times. Here comes the question: how much should the recommendations change? Should they remain the same, or should they rotate? Recombee API allows you to control this per-request in backward fashion. You may penalize an item for being recommended in the near past. For the specific user, rotationRate=1 means maximal rotation, rotationRate=0 means absolutely no rotation. You may also use, for example rotationRate=0.2 for only slight rotation of recommended items. More...
 
double? RotationTime [get]
 **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. More...
 
Dictionary< string, object > ExpertSettings [get]
 Dictionary of custom options. More...
 
bool? ReturnAbGroup [get]
 If there is a custom AB-testing running, return name of group to which the request belongs. More...
 
- Properties inherited from Recombee.ApiClient.ApiRequests.Request
TimeSpan Timeout [get, set]
 Timeout for the request in milliseconds More...
 
bool EnsureHttps [get]
 If true, HTTPS must be chosen over HTTP for this request More...
 
HttpMethod RequestHttpMehod [get]
 Used HTTP method More...
 

Additional Inherited Members

- Protected Member Functions inherited from Recombee.ApiClient.ApiRequests.Request
double ConvertToUnixTimestamp (DateTime date)
 
Returns
Converts DateTime to UNIX timestamp (epoch)
More...
 

Detailed Description

Recommend items to item

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. The returned items are sorted by relevance (first item being the most relevant). Besides the recommended items, also a unique recommId is returned in the response. It can be used to:

Constructor & Destructor Documentation

◆ RecommendItemsToItem()

Recombee.ApiClient.ApiRequests.RecommendItemsToItem.RecommendItemsToItem ( string  itemId,
string  targetUserId,
long  count,
string  scenario = null,
bool?  cascadeCreate = null,
bool?  returnProperties = null,
string[]  includedProperties = null,
string  filter = null,
string  booster = null,
Logic  logic = null,
double?  userImpact = null,
double?  diversity = null,
string  minRelevance = null,
double?  rotationRate = null,
double?  rotationTime = null,
Dictionary< string, object >  expertSettings = null,
bool?  returnAbGroup = null 
)
inline

Construct the request

Parameters
itemIdID of the item for which the recommendations are to be generated.
targetUserIdID of the user who will see the recommendations. Specifying the targetUserId is beneficial because:
  • It makes the recommendations personalized
  • Allows the calculation of Actions and Conversions in the graphical user interface, as Recombee can pair the user who got recommendations and who afterwards viewed/purchased an item. If you insist on not specifying the user, pass null (None, nil, NULL etc. depending on language) to targetUserId. Do not create some special dummy user for getting recommendations, as it could mislead the recommendation models, and result in wrong recommendations. For anonymous/unregistered users it is possible to use for example their session ID.
countNumber of items to be recommended (N for the top-N recommendation).
scenarioScenario defines a particular application of recommendations. It can be for example "homepage", "cart" or "emailing". You can set various settings to the scenario in the Admin UI. You can also see performance of each scenario in the Admin 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.
cascadeCreateIf item of given itemId or user of given targetUserId doesn't exist in the database, it creates the missing entity/entities and returns some (non-personalized) recommendations. This allows for example rotations in the following recommendations for the user of given targetUserId, as the user will be already known to the system.
returnPropertiesWith 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. Example response:
{
"recommId": "0c6189e7-dc1a-429a-b613-192696309361",
"recomms":
[
{
"id": "tv-178",
"values": {
"description": "4K TV with 3D feature",
"categories": ["Electronics", "Televisions"],
"price": 342,
"url": "myshop.com/tv-178"
}
},
{
"id": "mixer-42",
"values": {
"description": "Stainless Steel Mixer",
"categories": ["Home & Kitchen"],
"price": 39,
"url": "myshop.com/mixer-42"
}
}
],
"numberNextRecommsCalls": 0
}
Parameters
includedPropertiesAllows to specify, which properties should be returned when returnProperties=true is set. The properties are given as a comma-separated list. Example response for includedProperties=description,price:
{
"recommId": "6842c725-a79f-4537-a02c-f34d668a3f80",
"recomms":
[
{
"id": "tv-178",
"values": {
"description": "4K TV with 3D feature",
"price": 342
}
},
{
"id": "mixer-42",
"values": {
"description": "Stainless Steel Mixer",
"price": 39
}
}
],
"numberNextRecommsCalls": 0
}
Parameters
filterBoolean-returning ReQL expression which allows you to filter recommended items based on the values of their attributes. Filters can be also assigned to a scenario in the Admin UI.
boosterNumber-returning ReQL expression which allows you to boost recommendation rate of some items based on the values of their attributes. Boosters can be also assigned to a scenario in the Admin UI.
logicLogic specifies particular behavior of the recommendation models. You can pick tailored logic for your domain and use case. See this section for list of available logics and other details. The difference between logic and scenario is that logic specifies mainly behavior, while scenario specifies the place where recommendations are shown to the users. Logic can be also set to a scenario in the Admin UI.
userImpact**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.
diversity**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.
minRelevance**Expert option** If the targetUserId is provided: Specifies the threshold of how much relevant must the recommended items be to the user. Possible values one of: "low", "medium", "high". The default value is "low", meaning that the system attempts to recommend number of items equal to count at any cost. If there are not enough data (such as interactions or item properties), this may even lead to bestseller-based recommendations to be appended to reach the full count. This behavior may be suppressed by using "medium" or "high" values. In such case, the system only recommends items of at least the requested relevance, and may return less than count items when there is not enough data to fulfill it.
rotationRate**Expert option** If the targetUserId is provided: If your users browse the system in real-time, it may easily happen that you wish to offer them recommendations multiple times. Here comes the question: how much should the recommendations change? Should they remain the same, or should they rotate? Recombee API allows you to control this per-request in backward fashion. You may penalize an item for being recommended in the near past. For the specific user, rotationRate=1 means maximal rotation, rotationRate=0 means absolutely no rotation. You may also use, for example rotationRate=0.2 for only slight rotation of recommended items.
rotationTime**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.
expertSettingsDictionary of custom options.
returnAbGroupIf there is a custom AB-testing running, return name of group to which the request belongs.

Member Function Documentation

◆ BodyParameters()

override Dictionary<string, object> Recombee.ApiClient.ApiRequests.RecommendItemsToItem.BodyParameters ( )
inlinevirtual

Get body parameters

Returns
Dictionary containing values of body parameters (name of parameter: value of the parameter)

Implements Recombee.ApiClient.ApiRequests.Request.

◆ Path()

override string Recombee.ApiClient.ApiRequests.RecommendItemsToItem.Path ( )
inlinevirtual

Returns
URI to the endpoint including path parameters

Implements Recombee.ApiClient.ApiRequests.Request.

◆ QueryParameters()

override Dictionary<string, object> Recombee.ApiClient.ApiRequests.RecommendItemsToItem.QueryParameters ( )
inlinevirtual

Get query parameters

Returns
Dictionary containing values of query parameters (name of parameter: value of the parameter)

Implements Recombee.ApiClient.ApiRequests.Request.

Property Documentation

◆ Booster

string Recombee.ApiClient.ApiRequests.RecommendItemsToItem.Booster
get

Number-returning ReQL expression which allows you to boost recommendation rate of some items based on the values of their attributes. Boosters can be also assigned to a scenario in the Admin UI.

◆ CascadeCreate

bool? Recombee.ApiClient.ApiRequests.RecommendItemsToItem.CascadeCreate
get

If item of given itemId or user of given targetUserId doesn't exist in the database, it creates the missing entity/entities and returns some (non-personalized) recommendations. This allows for example rotations in the following recommendations for the user of given targetUserId, as the user will be already known to the system.

◆ Count

long Recombee.ApiClient.ApiRequests.RecommendItemsToItem.Count
get

Number of items to be recommended (N for the top-N recommendation).

◆ Diversity

double? Recombee.ApiClient.ApiRequests.RecommendItemsToItem.Diversity
get

**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.

◆ ExpertSettings

Dictionary<string, object> Recombee.ApiClient.ApiRequests.RecommendItemsToItem.ExpertSettings
get

Dictionary of custom options.

◆ Filter

string Recombee.ApiClient.ApiRequests.RecommendItemsToItem.Filter
get

Boolean-returning ReQL expression which allows you to filter recommended items based on the values of their attributes. Filters can be also assigned to a scenario in the Admin UI.

◆ IncludedProperties

string [] Recombee.ApiClient.ApiRequests.RecommendItemsToItem.IncludedProperties
get

Allows to specify, which properties should be returned when returnProperties=true is set. The properties are given as a comma-separated list. Example response for includedProperties=description,price:

{
"recommId": "6842c725-a79f-4537-a02c-f34d668a3f80",
"recomms":
[
{
"id": "tv-178",
"values": {
"description": "4K TV with 3D feature",
"price": 342
}
},
{
"id": "mixer-42",
"values": {
"description": "Stainless Steel Mixer",
"price": 39
}
}
],
"numberNextRecommsCalls": 0
}

◆ ItemId

string Recombee.ApiClient.ApiRequests.RecommendItemsToItem.ItemId
get

ID of the item for which the recommendations are to be generated.

◆ Logic

Logic Recombee.ApiClient.ApiRequests.RecommendItemsToItem.Logic
get

Logic specifies particular behavior of the recommendation models. You can pick tailored logic for your domain and use case. See this section for list of available logics and other details. The difference between logic and scenario is that logic specifies mainly behavior, while scenario specifies the place where recommendations are shown to the users. Logic can be also set to a scenario in the Admin UI.

◆ MinRelevance

string Recombee.ApiClient.ApiRequests.RecommendItemsToItem.MinRelevance
get

**Expert option** If the targetUserId is provided: Specifies the threshold of how much relevant must the recommended items be to the user. Possible values one of: "low", "medium", "high". The default value is "low", meaning that the system attempts to recommend number of items equal to count at any cost. If there are not enough data (such as interactions or item properties), this may even lead to bestseller-based recommendations to be appended to reach the full count. This behavior may be suppressed by using "medium" or "high" values. In such case, the system only recommends items of at least the requested relevance, and may return less than count items when there is not enough data to fulfill it.

◆ ReturnAbGroup

bool? Recombee.ApiClient.ApiRequests.RecommendItemsToItem.ReturnAbGroup
get

If there is a custom AB-testing running, return name of group to which the request belongs.

◆ ReturnProperties

bool? Recombee.ApiClient.ApiRequests.RecommendItemsToItem.ReturnProperties
get

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. Example response:

{
"recommId": "0c6189e7-dc1a-429a-b613-192696309361",
"recomms":
[
{
"id": "tv-178",
"values": {
"description": "4K TV with 3D feature",
"categories": ["Electronics", "Televisions"],
"price": 342,
"url": "myshop.com/tv-178"
}
},
{
"id": "mixer-42",
"values": {
"description": "Stainless Steel Mixer",
"categories": ["Home & Kitchen"],
"price": 39,
"url": "myshop.com/mixer-42"
}
}
],
"numberNextRecommsCalls": 0
}

◆ RotationRate

double? Recombee.ApiClient.ApiRequests.RecommendItemsToItem.RotationRate
get

**Expert option** If the targetUserId is provided: If your users browse the system in real-time, it may easily happen that you wish to offer them recommendations multiple times. Here comes the question: how much should the recommendations change? Should they remain the same, or should they rotate? Recombee API allows you to control this per-request in backward fashion. You may penalize an item for being recommended in the near past. For the specific user, rotationRate=1 means maximal rotation, rotationRate=0 means absolutely no rotation. You may also use, for example rotationRate=0.2 for only slight rotation of recommended items.

◆ RotationTime

double? Recombee.ApiClient.ApiRequests.RecommendItemsToItem.RotationTime
get

**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.

◆ Scenario

string Recombee.ApiClient.ApiRequests.RecommendItemsToItem.Scenario
get

Scenario defines a particular application of recommendations. It can be for example "homepage", "cart" or "emailing". You can set various settings to the scenario in the Admin UI. You can also see performance of each scenario in the Admin 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.

◆ TargetUserId

string Recombee.ApiClient.ApiRequests.RecommendItemsToItem.TargetUserId
get

ID of the user who will see the recommendations. Specifying the targetUserId is beneficial because:

  • It makes the recommendations personalized
  • Allows the calculation of Actions and Conversions in the graphical user interface, as Recombee can pair the user who got recommendations and who afterwards viewed/purchased an item. If you insist on not specifying the user, pass null (None, nil, NULL etc. depending on language) to targetUserId. Do not create some special dummy user for getting recommendations, as it could mislead the recommendation models, and result in wrong recommendations. For anonymous/unregistered users it is possible to use for example their session ID.

◆ UserImpact

double? Recombee.ApiClient.ApiRequests.RecommendItemsToItem.UserImpact
get

**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.


The documentation for this class was generated from the following file: