Pattern-based classification
A method includes receiving interaction data that indicates, for each given interaction among multiple interactions that occurred at a client device, (i) an event type an (ii) a delay period specifying an amount of time between the given event and a previous event that occurred prior to the given event, encoding each given interaction into an encoded interaction having a standardized format that is a combination of (i) the event type and (ii) the delay period, generating an interaction signature that includes sequence of encoded interactions, processing the sequence of encoded interactions using a model trained to label sequences of user interactions as valid or invalid, including labelling, using the model, a sequence of encoded interactions as invalid, and preventing distribution of a set of content to an entity that performed the sequence of encoded interactions in response to a subsequently identified request to provide content to the entity.
1 . A method performed by one or more data processing apparatus, the method comprising:
receiving interaction data for a sequence of user interactions with one or more electronic documents performed by an entity at a client device;
encoding the interaction data for the sequence of user interactions into encoded interaction data having a standardized format that is based on (i) an event type of each user interaction in the sequence of user interactions and (ii) a calculated time period indicating a duration of time elapsed between each of one or more user interactions in the sequence of user interactions and an immediately preceding user interaction in the sequence of user interactions;
providing the encoded interaction data for the sequence of user interactions to a trained machine learning model that is trained to classify sequences of user interactions as valid or invalid;
receiving, as an output of the trained machine learning model, a classification of the sequence of user interactions; and
controlling distribution of content to the entity based on the classification of the sequence of user interactions.
2 . The method of claim 1 , wherein controlling distribution of content to the entity based on the classification of the sequence of user interactions comprises distributing content to the entity in response to the classification of the sequence of user interactions being valid.
3 . The method of claim 1 , wherein controlling distribution of content to the entity based on the classification of the sequence of user interactions comprises reducing an amount of content distributed to the entity in response to the classification of the sequence of user interactions being invalid.
4 . The method of claim 1 , wherein controlling distribution of content to the entity based on the classification of the sequence of user interactions comprises adjusting distribution criteria for a digital component based on at least on the classification of the sequence of user interactions.
5 . The method of claim 4 , wherein adjusting the distribution criteria for the digital component comprises adjusting the distribution criteria based on classifications for multiple entities.
6 . The method of claim 1 , wherein the classification of the sequence of user interactions comprises a classification as an actual user or a classification as an automated bot.
7 . The method of claim 1 , wherein controlling distribution of content to the entity based on the classification of the sequence of user interactions comprises refraining for providing a specific type of content to the entity.
8 . The method of claim 1 , wherein encoding the interaction data for the sequence of user interactions into encoded interaction data having a standardized format comprises generating an interaction signature for the sequence of user interactions.
9 . The method of claim 1 , wherein encoding the interaction data for the sequence of user interactions into encoded interaction data having a standardized format comprises generating an interaction signature for each visit to a resource, wherein each interaction signature includes a portion of the sequence of user interactions.
10 . The method of claim 1 , wherein encoding the interaction data for the sequence of user interactions into encoded interaction data having a standardized format comprises generating an interaction signature for each user session of with a resource, wherein each interaction signature includes a portion of the sequence of user interactions.
11 . A system comprising:
one or more processors; and
one or more memory elements including instructions that, when executed, cause the one or more processors to perform operations comprising:
receiving interaction data for a sequence of user interactions with one or more electronic documents performed by an entity at a client device;
encoding the interaction data for the sequence of user interactions into encoded interaction data having a standardized format that is based on (i) an event type of each user interaction in the sequence of user interactions and (ii) a calculated time period indicating a duration of time elapsed between each of one or more user interactions in the sequence of user interactions and an immediately preceding user interaction in the sequence of user interactions;
providing the encoded interaction data for the sequence of user interactions to a trained machine learning model that is trained to classify sequences of user interactions as valid or invalid;
receiving, as an output of the trained machine learning model, a classification of the sequence of user interactions; and
controlling distribution of content to the entity based on the classification of the sequence of user interactions.
12 . The system of claim 11 , wherein controlling distribution of content to the entity based on the classification of the sequence of user interactions comprises distributing content to the entity in response to the classification of the sequence of user interactions being valid.
13 . The system of claim 11 , wherein controlling distribution of content to the entity based on the classification of the sequence of user interactions comprises reducing an amount of content distributed to the entity in response to the classification of the sequence of user interactions being invalid.
14 . The system of claim 11 , wherein controlling distribution of content to the entity based on the classification of the sequence of user interactions comprises adjusting distribution criteria for a digital component based on at least on the classification of the sequence of user interactions.
15 . The system of claim 14 , wherein adjusting the distribution criteria for the digital component comprises adjusting the distribution criteria based on classifications for multiple entities.
16 . The system of claim 11 , wherein the classification of the sequence of user interactions comprises a classification as an actual user or a classification as an automated bot.
17 . The system of claim 11 , wherein controlling distribution of content to the entity based on the classification of the sequence of user interactions comprises refraining for providing a specific type of content to the entity.
18 . A non-transitory computer storage medium encoded with instructions that when executed by a computing system cause the computing system to perform operations comprising:
receiving interaction data for a sequence of user interactions with one or more electronic documents performed by an entity at a client device;
encoding the interaction data for the sequence of user interactions into encoded interaction data having a standardized format that is based on (i) an event type of each user interaction in the sequence of user interactions and (ii) a calculated time period indicating a duration of time elapsed between each of one or more user interactions in the sequence of user interactions and an immediately preceding user interaction in the sequence of user interactions;
providing the encoded interaction data for the sequence of user interactions to a trained machine learning model that is trained to classify sequences of user interactions as valid or invalid;
receiving, as an output of the trained machine learning model, a classification of the sequence of user interactions; and
controlling distribution of content to the entity based on the classification of the sequence of user interactions.
19 . The non-transitory computer storage medium of claim 18 , wherein controlling distribution of content to the entity based on the classification of the sequence of user interactions comprises distributing content to the entity in response to the classification of the sequence of user interactions being valid.
20 . The non-transitory computer storage medium of claim 18 , wherein controlling distribution of content to the entity based on the classification of the sequence of user interactions comprises reducing an amount of content distributed to the entity in response to the classification of the sequence of user interactions being invalid.