基于移动用户浏览行为的推荐模型

推荐算法已经被广泛地应用于很多领域。但是如果利用传统的推荐算法预测移动用户浏览互联网的行为，并在此基础上对移动用户进行个性化的内容推荐，传统推荐算法的推荐效果往往比较差。该文通过分析移动用户浏览互联网的记录，得出传统推荐算法效果差的原因。在此基础上，提出了一个基于移动用户浏览行为的推荐模型，即RMBDMU。该模型可以对移动用户浏览互联网的行为进行预测，在预测的基础上对移动用户进行内容推荐。为了验证推荐模型的有效性，在真实的移动用户浏览互联网的行为数据上进行了实验。实验结果显示基于移动用户浏览行为的推荐模型比传统的推荐算法更为有效。

A Recommendation Model Based on Browsing Behaviors of Mobile Users

Recommendation algorithms have been commonly adopted in many fields. However, traditional recommendation algorithms fail to achieve the expected recommendation results if they are applied to predict browsing behaviors of the mobile users and further to recommend personalized content to the mobile users. By analyzing the Internet browsing data of the mobile users, this paper proposes a recommendation model based on browsing data of mobile users, denoted as RMBDMU, to predict the future browsing activities of the mobile users and take them as the bases to recommend contents to the mobile users. An experiment on the Internet browsing behavior data of the real mobile users is conducted to verify the effectiveness of the model. The experiment result shows that the recommendation model based on browsing data of mobile users is more effective than the traditional recommendation algorithms.