Enhancing the Accuracy and Fairness of Human Decision Making
Authors: Isabel Valera, Adish Singla, Manuel Gomez Rodriguez
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the effectiveness of our algorithms on both synthetic and real-world data and show that they can significantly improve both the accuracy and fairness of the decisions taken by pools of experts. |
| Researcher Affiliation | Academia | Isabel Valera MPI for Intelligent Systems ivalera@tue.mpg.de Adish Singla MPI-SWS adishs@mpi-sws.org Manuel Gomez-Rodriguez MPI-SWS manuelgr@mpi-sws.org |
| Pseudocode | No | The paper describes algorithms in text and through equations, but it does not provide formal pseudocode blocks or algorithms labeled as such. |
| Open Source Code | Yes | The implementations of our algorithms and the data used in our experiments are available at https://github.com/Networks-Learning/Fair Human Decisions. |
| Open Datasets | Yes | We use the COMPAS recidivism prediction dataset compiled by Pro Publica [8]... [8] J. Larson, S. Mattu, L. Kirchner, and J. Angwin. https://github.com/propublica/compas-analysis, 2016. |
| Dataset Splits | No | The paper states, "we train on 25% of the data. Then, we use the remaining 75% of the data to evaluate our algorithm as follows." It specifies a training and evaluation split but does not explicitly mention a validation set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments. |
| Software Dependencies | No | The paper mentions using a "logistic regression classifier" but does not specify software dependencies with version numbers (e.g., Python, PyTorch, Scikit-learn versions). |
| Experiment Setup | Yes | For every decision, we first sample the sensitive attribute zi {0, 1} from Bernouilli(0.5)... we set m = 20, T = 1000 and c = 0.5... we approximate pY |X,Z=z using a logistic regression classifier... we create N = 3m (fictitious) judges and sample their thresholds from a θ Beta(τ, τ)... we consider m = 20 decisions per round, which results into 197 rounds... |