E-Commerce Recommendation Applications
Data Mining and Knowledge Discovery
Eigentaste: A Constant Time Collaborative Filtering Algorithm
Information Retrieval
Evaluating collaborative filtering recommender systems
ACM Transactions on Information Systems (TOIS)
Latent semantic models for collaborative filtering
ACM Transactions on Information Systems (TOIS)
Content-based recommendation systems
The adaptive web
Hi-index | 0.00 |
Mobile reading on 'smart' terminals (like smartphones and tablet computers)is an increasing popular subject, and the recommendations of e-books for users also begin to attract more attentions. In this paper, we mainly demonstrate the performance of the personalized recommendation on the mobile reading platform, based on the analysis of the reading records on mobile phones. The analysis results of the feedback of users for the recommendations show that the personalized recommendation based on the mass diffusion algorithm is much better than the algorithm of the mobile company used before. In particular, both the number of the motivated page views and the motivated users have a dramatically increase. All these results indicate that the mass diffusion algorithm has an outstanding performance on the mobile reading recommendation, which can help users quickly find the books they are interested in. Meanwhile, it help the company enlarge the customer volume and improve the customer experience.