METHOD AND APPARATUS FOR ITEM RECOMMENDATION USING DEEP LEARNING

摘要

According to one embodiment of the present invention, a method for recommending an item using deep learning comprises the steps of: generating a purchase vector based on results that a plurality of users purchase at least one item among a plurality of items; generating a generation model based on the purchase vector; generating a determination model according to preset criteria; generating a final generation model based on the generation model and the determination model; and recommending the predetermined number of recommendation items among the items to at least one user among the users based on the final generation model. The method may perform more accurate recommendation.