/LORE

LOcal Rule-based Exlanations

Primary LanguageJavaScriptGNU General Public License v3.0GPL-3.0

LORE - LOcal Rule-based Explanations

This repository contains the source code of LORE (LOcal Rule-based Explanations) and the datasets used in the experiments presented in the paper "Local Rule-based Explanations of Black Box Decision Systems". This code has been used to carry on the experiemnts of the paper

Guidotti, R., Monreale, A., Giannotti, F., Pedreschi, D., Ruggieri, S., & Turini, F. (2019). Factual and counterfactual explanations for black box decision making. IEEE Intelligent Systems, 34(6), 14-23.

We encourage users to rely on the implemenation of LORE availabel here: https://kdd-lab.github.io/LORE_sa/html/index.html that is an improved version of the code adopted for the paper

Guidotti, R., Monreale, A., Ruggieri, S., Naretto, F., Turini, F., Pedreschi, D., & Giannotti, F. (2022). Stable and actionable explanations of black-box models through factual and counterfactual rules. Data Mining and Knowledge Discovery, 1-38.