Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/lpworld/PURS
https://github.com/lpworld/PURS
Last synced: about 7 hours ago
JSON representation
- Host: GitHub
- URL: https://github.com/lpworld/PURS
- Owner: lpworld
- Created: 2020-05-26T13:10:57.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2021-01-08T10:13:15.000Z (almost 4 years ago)
- Last Synced: 2024-08-02T13:21:28.495Z (3 months ago)
- Language: Python
- Size: 186 KB
- Stars: 42
- Watchers: 2
- Forks: 13
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# PURS
This is our implementation for the paper:
**Pan Li, Maofei Que, Zhichao Jiang, Yao Hu and Alexander Tuzhilin. "PURS: Personalized Unexpected Recommender System for Improving User Satisfaction." Proceedings of the 14th ACM Conference on Recommender Systems. 2020.** [[Paper]](https://lpworld.github.io/files/recsys20.pdf)
**Dataset:** [[Yelp dataset]](https://www.yelp.com/dataset) [[MovieLens Dataset]](https://grouplens.org/datasets/movielens/)
Due to the confidential agreement with the Youku company, we are not allowed to make the Youku dataset publicly available. Nevertheless, you are always welcome to use our codes for the two public datasets and your own dataset.**Please cite our RecSys'20 paper if you use our codes. Thanks!**
Author: Pan Li (https://lpworld.github.io/)
## Environment Settings
We use Tensorflow as the backend.
- Tensorflow version: '1.4.0'## Example to run the codes.
The instruction of commands has been clearly stated in the codes (see the parse_args function).Run PURS:
```
python train.py
```## Acknowledgement
This implementation is inspired from [Deep Interest Network](https://github.com/zhougr1993/DeepInterestNetwork).Last Update: 2020/07/27