Systems and methods for providing personalized discounted items

A method comprising:

• obtaining savings data including savings items;
• obtaining, by a discounted item recommendation model and based on semantic similarities between a plurality of items, a plurality of clusters, each cluster of the plurality of clusters includes a set of product types;
• obtaining user data associated with a user;
• determining, by the discounted item recommendation model, a set of initial items for recommendation based on the savings data and the plurality of clusters, the set of initial items includes a subset of the savings items;
• and
• determining, by the discounted item recommendation model, final recommendation items for the user based on the set of initial items and the user data.

A non-transitory computer readable medium having instructions stored thereon, wherein the instructions, when executed by at least one processor, cause a device to perform operations comprising:

• obtaining savings data including savings items;
• obtaining, by a discounted item recommendation model and based on semantic similarities between a plurality of items, a plurality of clusters, each cluster of the plurality of clusters includes a set of product types;
• obtaining user data associated with a user;
• determining, by the discounted item recommendation model, a set of initial items for recommendation based on the savings data and the plurality of clusters, the set of initial items includes a subset of the savings items;
• and
• determining, by the discounted item recommendation model, final recommendation items for the user based on the set of initial items and the user data.