A Tensorflow based implicit recommender system
A-RecSys implements implicit recommendation algorithms and is designed for large scale recommendation settings. It extends traditional matrix factorization algorithms, and focuses on attribute embedding and applying sequence models.
Works implemented by this toolkit include:
The models and features supported by A-RecSys include,
CSV-formated (sep=\t) input files include
u.csv : user file. user id and attribute values.
i.csv: item file. item id and attribute values.
obs_tr.csv: implicit feedback for training. First two columns are user-id, item-id. Third column (optional) is for timestamp.
obs_va.csv: implicit feedback for development.
obs_te.csv: implicit feedback for testing.
A example (adapted from MovieLens 1m) is given at ./examples/dataset/
Example scripts are provided at ./examples/ to start running the code
To train hybrid matrix factorization model on provided MovieLens 1m dataset:
cd examples/
bash run_hmf.sh 32 1 False 100 False
To train lstm model:
cd examples/
bash run_lstm.sh 64 1 False
(Code has been tested on TF 0.8 and above.)
You can switch to "recommend" mode from "training" by setting flag recommend to 'true'. In the above HMF example, it would be:
cd examples/
bash run_hmf.sh 32 1 False 100 True
By default, the code generates a ground truth interaction file res_T_test.csv from obs_te.csv, and perform recommendation on all users that appear in res_T_test.csv. You can generate your own res_T_test.csv to narrow down user set to identify which recommendation is being performed.
The code now supports Tensorflow v1.0. During our development, the code was tested with versions 0.8, 0.9, 0.11, 0.12.
Please cite the following if you find this helpful.
@inproceedings{liu2017wmrb, title={WMRB: learning to rank in a scalable batch training approach}, author={Liu, Kuan and Natarajan, Prem}, booktitle={Proceedings of the Recommender Systems Poster}, year={2017}, organization={ACM} }
@inproceedings{liu2016temporal, title={Temporal learning and sequence modeling for a job recommender system}, author={Liu, Kuan and Shi, Xing and Kumar, Anoop and Zhu, Linhong and Natarajan, Prem}, booktitle={Proceedings of the Recommender Systems Challenge}, pages={7}, year={2016}, organization={ACM} }
Your comments and suggestions are more than welcome! We really appreciate that!
Kuan Liu [email protected] Xing Shi [email protected]