Conversion optimization with long attribution window

A system, comprising:

• a processor;
• a memory storing instructions, which when executed by the processor, cause the processor to:
• selecting, from a plurality of candidate content items, a subset of the plurality of candidate content items to be displayed to a target user;
• predicting, for each of the subset of the plurality of candidate content items, that the target user will convert given an interaction with content by the target user;
• determining, using an additive conversion probability technique, a probability that the user will convert given an interaction with the content by the target user;
• and
• ranking the subset of the plurality of candidate content items to be selected and displayed to the target user based on the determined probability.

A method, comprising:

• selecting, by a processor, from a plurality of candidate content items, a subset of the plurality of candidate content items to be displayed to a target user;
• predicting, for each of the subset of the plurality of candidate content items, that the target user will convert given an interaction with content by the target user;
• determining, using an additive conversion probability technique, a probability that the user will convert given an interaction with the content by the target user;
• and
• ranking the subset of the plurality of candidate content items to be selected and displayed to the target user based on the determined probability.

A non-transitory computer-readable storage medium having an executable stored thereon, which when executed instructs a processor to:

• select, from a plurality of candidate content items, a subset of the plurality of candidate content items to be displayed to a target user;
• predicting, for each of the subset of the plurality of candidate content items, that the target user will convert given an interaction with content by the target user;
• determining, using an additive conversion probability technique, a probability that the user will convert given an interaction with the content by the target user;
• and
• ranking the subset of the plurality of candidate content items to be selected and displayed to the target user based on the determined probability.