Content recommendation techniques with reduced habit bias effects

A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:

• constructing a content selection vector for a customer device based on content consumption data for the customer device, wherein the content consumption data is associated with media content consumption at the customer device;
• determining a habit-based content selection vector for the customer device, wherein the habit-based content selection vector identifies media content consumption in a habitual, regular fashion for the customer device;
• removing content identified by the habit-based content selection vector from the content consumption data for the customer device to generate an adjusted content selection vector for the customer device;
• and
• generating a content selection recommendation for the customer device based on the adjusted content selection vector.

A method, comprising:

• determining, by a processing system comprising a processor, a habit-based content selection vector for a customer device, wherein the habit-based content selection vector identifies media content consumption in a habitual, regular fashion for the customer device;
• removing, by the processing system, content identified by the habit-based content selection vector from content consumption data for the customer device to generate an adjusted content selection vector for the customer device;
• and
• generating, by the processing system, a content selection recommendation for the customer device based on the adjusted content selection vector.