ML-Based Feature Importance Estimation for Predicting Unethical Behaviour under Pressure

Abstract : We studied the utility of using machine learning algorithms in the estimation of feature importance and to visualize their dependence on Ethicality. Through our analysis and partial dependence plot we found linear relationships among variables and gained insight into features that might cause certain types of ethical behaviour.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02264914
Contributor : Pablo Rivas <>
Submitted on : Wednesday, August 7, 2019 - 7:33:33 PM
Last modification on : Saturday, August 10, 2019 - 1:11:19 AM

Identifiers

  • HAL Id : hal-02264914, version 1

Collections

Citation

Pablo Rivas, Pamela Harper, John Cary, William Brown. ML-Based Feature Importance Estimation for Predicting Unethical Behaviour under Pressure. LatinX in AI Research at ICML 2019, Jun 2019, Long Beach, CA, United States. ⟨hal-02264914⟩

Share

Metrics

Record views

25

Files downloads

11