Authors: Sopam Dasgupta, Farhad Shakerin, Joaquín Arias, Elmer Salazar, Gopal Gupta

Published on: February 06, 2024

Impact Score: 8.05

Arxiv code: Arxiv:2402.04382

Summary

• What is new: The paper proposes a new framework, CFGS, that combines answer set programming with s(CASP) for generating counterfactual explanations from machine learning predictions.
• Why this is important: The lack of transparency in machine learning models used in critical decision-making processes.
• What the research proposes: A framework named Counterfactual Generation with s(CASP) (CFGS) that generates counterfactual explanations to enhance model transparency.
• Results: The framework successfully generates and navigates between different ‘worlds’ to provide counterfactual explanations for desired outcomes.

Technical Details

Technological frameworks used: Counterfactual Generation with s(CASP) (CFGS)

Models used: Rule-based machine learning algorithms

Data used: Rules generated by RBML algorithms

Potential Impact

Finance, legal, HR, and any sector employing algorithmic decision-making could benefit or need to adapt.

Want to implement this idea in a business?

We have generated a startup concept here: Explainify.