Systems and methods including a machine-learnt model for retrieval

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

• receiving a target string;
• obtaining a set of candidate items based on the target string;
• ranking the set of candidate items based on a scoring function, wherein the scoring function includes a plurality of simultaneously determined coefficients, wherein the plurality of simultaneously determined coefficients are generated by a trained ranking model, wherein the scoring function is:
• score
• =
• ∑
• i
• =
• 1
• n
• c
• i
• *
• P
• i
• where Pi is an ith feature of a candidate item in the set of candidate items, ci is a coefficient corresponding to the ith feature selected from the plurality of simultaneously determined coefficients, and n is the total number of features for the candidate item;
• and
• outputting a set of N items selected from the set of candidate items based on the ranking.

A method, comprising:

• receiving a target string;
• obtaining a set of candidate items based on the target string;
• ranking the set of candidate items based on a scoring function, wherein the scoring function includes a plurality of simultaneously determined coefficients, wherein the plurality of simultaneously determined coefficients are generated by a trained ranking model trained using a set of combined relevance and engagement labels;
• and
• outputting a set of N items selected from the set of candidate items based on the ranking.