lgsaber/recurrent-intensity-model-experiments

Recurrent Intensity Model Experiments

Repository to reproduce the experiments in the paper:

Yifei Ma, Ge Liu Anoop Deoras. Recurrent Intensity Modeling for User Recommendation and Online Matching. ICML 2021 Time-Series Workshop. link1 link2

Getting Started

1. Download and install via pip install -e . Additional conda dependencies may be found at environment.yml
2. Add data to the data folder. Some downloading and preparing scripts may be found in data/util.py.
3. Run experiment as

   from rim_experiments import main, plot_results
   self = main("prepare_ml_1m_data", lb_mult=[0.5, 0.2, 0.1, 0])
   fig = plot_results(self)
   

   
4. To extend to other datasets, see example in prepare_synthetic_data
5. The provided examples are tested in test.

Security

See CONTRIBUTING for more information.

License

This project is licensed under the Apache-2.0 License.