Improving Consumer Experience With Pre-Purify Temporal-Decay Memory-Based Collaborative Filtering Recommendation for Graduate School Application

Abstract

The Internet is booming with information, and it has become especially difficult for consumers to sift through the information. Recommendation systems can effectively enhance the consumer experience. However, model-based recommendation systems require sufficient training data, so they perform poorly in small-scale recommendation scenarios such as graduate school recommendation. To this end, we focus on online recommendation in graduate school application scenarios. We propose a Pre-purify Temporal-decay Memory-based Collaborative Filtering model called PTMCF, which firstly improves the data quality based on the users’ background information by pre-purifying the data to compensate for the poor performance caused by the small dataset. At the same time, considering that user preferences and the importance of information are constantly changing, we propose incorporating Newton’s Law of Cooling when constructing the user-item scoring matrix to assign time-based weights. Experiments on a dataset collected from real-world questionnaires show that pre-purify and temporal-decay effectively improve recommendation quality and mitigate the impact of data sparsity on memory-based collaborative filtering.