Collaborative Filtering Skyline (CFS) for Enhanced Recommender Systems
G. Shobana, Ahmed A. Elngar · 2023
Collaborative filtering (CF) systems exploit previous ratings and similarity in user behavior to recommend the top-k objects/records which are potentially most interesting to the user assuming a single score per object. However, in various applications, a record (e.g., hotel) may be rated on several attributes (value, service, etc.), in which case simply returning the ones with the highest overall scores fails to capture the individual attribute characteristics and accommodate different selection criteria. To enhance the flexibility of CF, we propose Collaborative Filtering Skyline (CFS), a general framework that combines the advantages of CF with those of the skyline operator. CFS generates a personalized skyline for each user based on scores of other users with similar behavior. The personalized skyline includes objects that are good in certain aspects and eliminates the ones that are not interesting in any attribute combination. Although the integration of skylines and CF has several attractive properties, it also involves rather expensive computations. We face this challenge through a comprehensive set of algorithms and optimizations that reduce the cost of generating personalized skylines. We propose the top-k personalized skyline, where the user specifies the required output cardinality. We propose to Create an online web application to allow users to log in, view, search and upload videos. The videos can be uploaded by any user under different categories with a brief description of the movie. The purpose of this module is to form the base application for which we will apply the concept of skyline-based recommendation. We will allow the users to rate the movies on the site based on different attributes. The attribute ratings are collected for each user for each movie and stored in the database for later analysis. The rating data forms the basis of data collection for this project. This data is then analyzed to allow the recommendation system to finalize the recommendation list of items. By applying the concept of skylines, the skyline items for each attribute are computed for the logged-in user. The personalized skylines are computed. To be able to finalize the recommendation list by computing the top personalized skylines. The top list will differ for each user. Based on skyline computation results, the list of movies to be recommended are generated and displayed to the logged-in user.