Effective multi-scale multi-granular targeting for game users

An apparatus comprising:

• at least one processing device configured to:
• obtain, based on a sequential graph-based model, gaming exposure information over time, the gaming exposure information including device-level preferences and household-level preferences;
• combine one or more raw user behavior sessions into a gameplay session based on the obtained gaming exposure information;
• provide a scoring metric to (i) check an extent of multi-matching in the obtained gaming exposure information and (ii) remove untrustworthy gaming exposures from the obtained gaming exposure information;
• and
• generate, based on a feature engineering pipeline, one or more game segments running in a production environment, the one or more game segments identified for ancillary content based on inferences by a machine learning model trained using the gaming exposure information.

A non-transitory computer readable medium containing instructions that when executed cause at least one processor to:

• obtain, based on a sequential graph-based model, gaming exposure information over time, the gaming exposure information including device-level preferences and household-level preferences;
• combine one or more raw user behavior sessions into a gameplay session based on the obtained gaming exposure information;
• provide a scoring metric to (i) check an extent of multi-matching in the obtained gaming exposure information and (ii) remove untrustworthy gaming exposures from the obtained gaming exposure information;
• and
• generate, based on a feature engineering pipeline, one or more game segments running in a production environment, the one or more game segments identified for ancillary content based on inferences by a machine learning model trained using the gaming exposure information.

A method comprising:

• generating device-level advertising targeting inferences and household-level advertising targeting inferences for one or more game segments running in a production environment using inferencing by a machine learning model trained using a feature engineering pipeline to weight features according to gaming exposure information obtained over time, the gaming exposure information including at least device-level preferences and household-level preferences;
• determining, based on an aggregation level specified by input data, that genre-level advertising targeting inferences are needed;
• and
• from the device-level and household-level advertising targeting inferences, generating genre-level advertising targeting inferences relating to the one or more game segments using inferencing by the machine learning model.