Content recommendation based upon continuity and grouping information of attributes
One or more computing devices, systems, and/or methods for content recommendation based upon continuity and grouping information of attributes are provided herein. User interaction data specifying whether users interacted with content items, user attributes of the users, and content attributes of the content items is obtained. A data structure is populated with the user interaction data. The data structure is modified by inserting a set of sub-fields into the data structure for a user attribute. A sub-field is populated with a value representing an option of the user attribute. The set of sub-fields are an encoding of continuity information and grouping information representing options for the user attribute. The data structure is processed using machine learning functionality to generate a model. The model is utilized to generate a prediction as to whether a user will interact with a content item.
1 . A method, comprising:
executing, on a processor of a computing device, instructions that cause the computing device to perform operations, the operations comprising:
modifying a data structure by inserting a plurality of sub-fields for a single user attribute associated with a plurality of possible attribute values, wherein the plurality of sub-fields represent a single attribute value of the single user attribute in a distributed encoded form; and
at least one of generating or training a model utilizing the data structure.
2 . The method of claim 1 , comprising:
populating the plurality of sub-fields with gray code information corresponding to options for the user attribute.
3 . The method of claim 1 , wherein the data structure comprises a table and user attribute values of the user attribute are populated within a first set of fields within a first column of the table.
4 . The method of claim 3 , wherein content attribute values of a content attribute are populated within a second set of fields within a second column of the table.
5 . The method of claim 4 , wherein user interaction indicator values are populated within a third set of fields within a third column of the table.
6 . The method of claim 3 , wherein the plurality of sub-fields correspond to a set of columns inserted into the table for the user attribute.
7 . The method of claim 1 , comprising:
utilizing the data structure to rank two or more content items based upon a likelihood a user will interact with the two or more content items.
8 . The method of claim 7 , comprising:
transmitting a content item, having a rank above a threshold, over a network to a computer for display to the user.
9 . The method of claim 1 , comprising:
populating the plurality of sub-fields with cyclic gray code information corresponding to options for the user attribute.
10 . The method of claim 1 , comprising:
populating the plurality of sub-fields with monotonic gray code information corresponding to options for the user attribute.
11 . The method of claim 1 , comprising:
populating the plurality of sub-fields with gray code values corresponding to options for the user attribute, wherein consecutive gray code values differ by a single digit.
12 . The method of claim 1 , wherein the model is at least one of generated or trained utilizing a factorization machine.
13 . A computing device comprising:
a processor; and
memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising:
modifying a data structure by inserting a plurality of sub-fields for a single user attribute associated with a plurality of possible attribute values, wherein the plurality of sub-fields represent a single attribute value of the single user attribute in a distributed encoded form; and
at least one of generating or training a model utilizing the data structure.
14 . The computing device of claim 13 , wherein the operations comprise:
populating the plurality of sub-fields with gray code information corresponding to options for the user attribute.
15 . The computing device of claim 13 , wherein the data structure comprises a table and user attribute values of the user attribute are populated within a first set of fields within a first column of the table.
16 . The computing device of claim 15 , wherein content attribute values of a content attribute are populated within a second set of fields within a second column of the table, and wherein.
17 . The computing device of claim 15 , wherein user interaction indicator values are populated within a second set of fields within a second column of the table.
18 . The computing device of claim 15 , wherein the plurality of sub-fields correspond to a set of columns inserted into the table for the user attribute.
19 . A non-transitory machine readable medium having stored thereon processor-executable instructions that when executed cause performance of operations, the operations comprising:
modifying a data structure by inserting a plurality of sub-fields for a single attribute associated with a plurality of possible attribute values, wherein the plurality of sub-fields represent a single attribute value of the single attribute in a distributed encoded form; and
at least one of generating or training a model utilizing the data structure.
20 . The non-transitory machine readable medium of claim 19 , wherein the operations comprise:
utilizing the data structure to rank two or more content items based upon a likelihood a user will interact with the two or more content items; and
transmitting a content item, having a rank above a threshold, over a network to a computer for display to the user.