PERSCEN

---

Requirements

conda env create -f environment.yml

Instructions to prepare dataset

cd datasets
# KuaiRand-Pure
bash download_kuairand_pure.sh

# Alimama
bash download_alimama.sh

Instructions to run the experiment

# KuaiRand-Pure
bash scripts/kuairand-pure/perscen.sh

# Alimama
bash scripts/alimama/perscen.sh

Citation

Readers are welcomed to fork this repository to reproduce the experiments and follow our work. Please kindly cite our paper:

@inproceedings{du2025perscen,
  title={PERSCEN: Learning Personalized Interaction Pattern and Scenario Preference for Multi-Scenario Matching},
  author={Du, Haotong and Wang, Yaqing and Xiong, Fei and Shao, Lei and Liu, Ming and Gu, Hao and Yao, Quanming and Wang, Zhen},
  booktitle={Proceedings of the 31th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
  year={2025}
}

Acknowledgement

The release code is partially based on the codes of torch-rechub and CAGE. We thank the authors of above work.