Collaborative Evolution for User Profiling in Recommender Systems
Authors: Zhongqi Lu, Sinno Jialin Pan, Yong Li, Jie Jiang, Qiang Yang
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | To verify the effectiveness of the proposed model, we conduct experiments on a real-world dataset, which is obtained from the online shopping website of Tencent Inc. www.51buy.com and contains more than 1 million users shopping records in a time span of more than 180 days. Experimental analyses demonstrate that our proposed CE model can be used to make better future recommendations compared to several stateof-the-art methods. |
| Researcher Affiliation | Collaboration | Hong Kong University of Science and Technology, Hong Kong Nanyang Technological University, Singapore ]VIPSHOP, China Tencent, China |
| Pseudocode | Yes | Algorithm 1 Collaborative Evolution |
| Open Source Code | Yes | For further evaluations and future researches, the full dataset and the code in the experiments are released at http://zhongqi.me. |
| Open Datasets | Yes | For further evaluations and future researches, the full dataset and the code in the experiments are released at http://zhongqi.me. |
| Dataset Splits | No | The paper describes varying training set sizes (e.g., "CE 5Train, CE 15Train, CE 30Train, and CE 50Train") and specifies the test set ("For testing, we use data from August 22, 2013 onwards"). However, it does not provide explicit details about a separate validation set or specific percentages for train/validation/test splits needed to reproduce data partitioning. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU models, CPU types, or memory used for running the experiments. It only mentions general experimental settings. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., Python 3.8, PyTorch 1.9) required to replicate the experiment. |
| Experiment Setup | Yes | In our experiments, we make the duration of each time interval to be one day. From the browsing log, we first construct an user-item matrix for each day. The cell value of the matrix is the count of a user s daily browsing an item. We further normalize each user-item matrix such that for each user, the sum of the item browsing, if is not 0, is equal to 1. |