Improving Screening Processes via Calibrated Subset Selection

This repo contains the code for the empirical evaluation in the paper Improving Screening Processes via Calibrated Subset Selection, which includes an implementation of the Calibrated Subset Selection algorithm proposed in the paper.

Create Environment

Make sure conda is installed. Run

conda env create -f environment.yml
source activate alg_screen

Download and Prepare Data

Set prepare_data = True and submit = False in params_exp_noise.py and params_exp_diversity_noise.py

Run

python ./scripts/run_exp_noise.py
python ./scripts/run_exp_diversity_noise.py

Run Experiments

Set prepare_data = False and submit = True in params_exp_noise.py and params_exp_diversity_noise.py

On a cluster with Slurm workload manager, run

python ./scripts/run_exp_noise.py
python ./scripts/run_exp_cal_size.py
python ./scripts/run_exp_diversity_noise.py

Plot Figures

Run

python ./scripts/plot_exp_normal.py
python ./scripts/plot_exp_diversity.py

Bibtex

@article{wang2022improving,
  title={Improving Screening Processes via Calibrated Subset Selection},
  author={Wang, Lequn and Joachims, Thorsten and Rodriguez, Manuel Gomez},
  journal={arXiv preprint arXiv:2202.01147},
  year={2022}
}