Probabilistic recommendation of an item

Abstract

A clustering and recommendation machine determines that an item is included in a cluster of items. The machine accesses item data descriptive of the item. The machine accesses a vector that represents the cluster and calculates the likelihood that the item is included in the cluster, based on the item variable and the probability parameter. The machine determines that the item is included in the cluster, based on the likelihood. The machine also recommends an item to a potential buyer. The machine accesses behavior data that represents a first event type pertinent to a first cluster of items. The machine calculates a probability that a second event type pertaining to a second cluster of items will co-occur with the first event type. The machine identifies an item from the second cluster to be recommended and presents a recommendation of the item to the potential buyer.

1 . (canceled) 
     
     
         2 . A system comprising:
 one or more hardware processors; and   a memory storing instructions that, when executed by the one or more hardware processors, cause the one or more hardware processors to perform operations comprising:
 accessing, from a database, data pertinent to a first cluster of items representing a first product, the data including an event record representative of a first event type applicable to the first product; 
 calculating, based on the data, a probability of occurrence of the first event type with a second event type, the second event type pertaining to a second product represented by a second cluster of items, the second cluster including an item to be recommended, the calculating comprising generating a matrix of occurrences based on the data; 
 identifying the item to be recommended based on the probability of co-occurrence; and 
 causing presentation of a recommendation of the item. 
   
     
     
         3 . The system of  claim 2 , wherein the calculating the probability of occurrence further comprises calculating an argument of a maximum of the probability of co-occurrence. 
     
     
         4 . The system of  claim 2 , wherein the operations further comprise determining that an instance of the first event type and an instance of the second event type occurred within a threshold time period. 
     
     
         5 . The system of  claim 2 , wherein the operations further comprise:
 accessing item data describing the item, the item data being unstructured data and including an item variable;   accessing a vector representing the second cluster of items, the vector including a probability parameter;   calculating a result based on the item variable and the probability parameter;   determining that the item is included in the second cluster based on the result; and   storing a map file that includes a correspondence between the item and the second cluster.   
     
     
         6 . The system of  claim 2 , wherein the operations further comprise removing a portion of the data based on a number of activities performed by a user within a threshold time period, the data comprising behavior data of the user. 
     
     
         7 . The system of  claim 2 , wherein the operations further comprise accessing popularity data pertinent to the first product, the identifying the item to be recommended being further based on the popularity data. 
     
     
         8 . The system of  claim 2 , wherein the operations further comprise accessing a trust score of a seller of the item, the identifying the item to be recommended being further based on the trust score. 
     
     
         9 . The system of  claim 2 , wherein the operations further comprise determining a rank of the item to be recommended to the potential buyer, the causing presentation of the recommendation being based on the rank of the item. 
     
     
         10 . The system of  claim 9 , wherein the operations further comprise:
 accessing a deadline of the item, the deadline indicating a time after which the item is unavailable, the determining the rank of the item being based on the deadline.   
     
     
         11 . The system of  claim 2 , wherein the causing the presentation comprises causing a display of unstructured item data descriptive of the item and indicating the item as a specimen of the second product. 
     
     
         12 . The system of  claim 2 , wherein:
 the data includes position data of a hyperlink presented in a web page, the hyperlink being to request information pertinent to the first product; and   the calculating of the probability is based on the position data.   
     
     
         13 . A method comprising:
 accessing, from a database, data pertinent to a first cluster of items representing a first product, the data including an event record representative of a first event type applicable to the first product;   calculating, by a hardware processor and based on the data, a probability of occurrence of the first event type with a second event type, the second event type pertaining to a second product represented by a second cluster of items, the second cluster including an item to be recommended, the calculating comprising generating a matrix of occurrences based on the data;   identifying the item to be recommended based on the probability of co-occurrence; and   causing presentation of a recommendation of the item.   
     
     
         14 . The method of  claim 13 , wherein the calculating the probability of occurrence further comprises calculating an argument of a maximum of the probability of co-occurrence. 
     
     
         15 . The method of  claim 13 , further comprising determining that an instance of the first event type and an instance of the second event type occurred within a threshold time period. 
     
     
         16 . The method of  claim 13 , further comprising:
 accessing item data describing the item, the item data being unstructured data and including an item variable;   accessing a vector representing the second cluster of items, the vector including a probability parameter;   calculating, by a hardware processor, a result based on the item variable and the probability parameter;   determining that the item is included in the second cluster based on the result; and   storing a map file that includes a correspondence between the item and the second cluster.   
     
     
         17 . The method of  claim 13 , further comprising accessing popularity data pertinent to the first product, wherein the identifying the item to be recommended is further based on the popularity data. 
     
     
         18 . The method of  claim 13 , further comprising accessing a trust score of a seller of the item, wherein the identifying the item to be recommended is further based on the trust score. 
     
     
         19 . The method of  claim 13 , further comprising:
 accessing a deadline of the item, the deadline indicating a time after which the item is unavailable; and   determining a rank of the item to be recommended to the potential buyer based on the deadline, wherein the causing presentation of the recommendation is based on the rank of the item.   
     
     
         20 . The method of  claim 13 , wherein:
 the data includes position data of a hyperlink presented in a web page, the hyperlink being to request information pertinent to the first product; and   the calculating of the probability is based on the position data.   
     
     
         21 . A hardware storage device storing instructions that, when executed by the one or more hardware processors, cause the one or more hardware processors to perform operations comprising:
 accessing, from a database, data pertinent to a first cluster of items representing a first product, the data including an event record representative of a first event type applicable to the first product;   calculating, based on the data, a probability of occurrence of the first event type with a second event type, the second event type pertaining to a second product represented by a second cluster of items, the second cluster including an item to be recommended, the calculating comprising generating a matrix of occurrences based on the data;   identifying the item to be recommended based on the probability of co-occurrence; and   causing presentation of a recommendation of the item.