Abstract

With the construction and development of smart cities and the increasing needs of people, big data algorithm recommendations in the public services of smart cities can better provide people with content or items that meet their hobby needs, and enterprises in innovative application services can upgrade their products and contents according to people's needs. To address the problems of low accuracy and large bias in today's big data recommendation algorithm. In this paper, we will take a book recommendation system as an example, aiming at solving the problems of lack of cold boot in old book recommendation algorithms, the broad classification of collaborative filtering algorithms, and inconspicuous preference bias. To find the improvement in the F1 measure after the improvement of the recommendation algorithm. In addition, put the experimental improved recommendation algorithm into the take-out recommendation on campus to find the feasibility of the recommendation algorithm.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call