Improved Recommendation Sorting of Collaborative Filtering Algorithm

Abstract

Abstract. The traditional collaborative filtering algorithm has no overall quantitative understanding on users' preference. This paper proposes a collaborative filtering algorithm based on improved recommendation sorting. Based on the traditional collaborative filtering rating prediction, three kinds of weighted sorting strategies are proposed to recommendation list, which are based on the combination of users' preference vector and item quality. Experiments on the MovieLens data set show that, in the same rating prediction process, the recommended results of the improved sorting have a significant increase of nearly one time in the precision, recall and F1 indicators.

Application of mathematical expression-based recommendation models in user behaviour modelling

“…Traditional recommendation models can only process specific information, which cannot meet the requirements of different types of users for product characteristics and personalisation at different times and in various application scenarios. This paper focuses on the useful data obtained during the modelling process of predicting audience behaviour based on mathematical expressions, and applying them to the algorithm to obtain the corresponding performance indicators [8]. After the results of the expected utility function, correlation error size and regression analysis, it is experimentally demonstrated that the recommendation model can solve many practical problems, improve the efficiency and accuracy of the recommendation when processing information, and the performance of the algorithm model is greatly improved.…”

Improvement of Collaborative Filtering Recommendation Algorithm Based on Intuitionistic Fuzzy Reasoning Under Missing Data

“…The collaborative filtering recommendation algorithm is the earliest and well-applied recommendation algorithm, which is used primarily for preference prediction and item recommendation. By mining a specified user's historical behavior data, the algorithm analyzes the user's interest, finds other users with similar interest in the user set, synthesizes the evaluation of these related users on certain items, forms the system's preference prediction for the items, and finally recommends items with similar interest for the user [19], [20].…”