User Travel Preference Data Analysis Platform based on Big Data

Authors

  • Liping Wang

Abstract

In recent years, group recommendation system has gradually become one of the research hotspots in tourism recommendation field. The problem of data sparsity faced by traditional recommendation system also exists in group recommendation system. In the rating based recommendation system, the group recommendation system can be divided into two stages: the prediction of individual user's preference and the fusion of the prediction results of group members. In order to improve the effect of recommendation, this paper proposes a tourism group recommendation method which combines collaborative filtering and user preference. It considers the accuracy of user's prediction score and group recommendation results. In collaborative filtering, similarity influence factor and correlation factor are added to predict score. Then, based on mean value strategy and minimum pain strategy, satisfaction balance strategy is proposed, which considers local satisfaction and overall satisfaction of members in the group. Experiments show that the proposed method improves the accuracy of recommendation.

Published

2020-04-30

Issue

Section

Articles