Algorithmic Recourse based on User’s Feature-order Preference

Singh, Manan and Kancheti, Sai Srinivas and Gupta, Shivam and Ghalme, Ganesh and Jain, Shweta and C. Krishnan, Narayanan (2023) Algorithmic Recourse based on User’s Feature-order Preference. In: Conference on Data Science and Management of Data, CODS-COMAD 2023, 4-7, January 2023, Mumbai.

Text
3570991.3571039.pdf - Published Version
Download (521kB)

Abstract

The state-of-the-art recourse generation methods solely rely on the user's profile (feature vector). However, two users having the same profile may still have different preferences. Consequently, the recourse generated from a single profile may not have the same appeal to both the users. For example, one rejected loan applicant may prefer changes in Savings Amount, whereas, another - being a financial expert - may prefer changes in Investment Amount. Taking into account these preferences in feature-change can be very helpful in generating more user-satisfying recourses. To this end, we propose a simple user-preference representation and design a method to generate a recourse that adheres to the user preference. We empirically demonstrate the effectiveness and ease of the proposed method at generating recourses satisfying user preferences.

[error in script]

IITH Creators:

IITH Creators	ORCiD
Ghalme, Ganesh	http://www.orcid.org/0000-0001-5049-4764

Item Type:

Conference or Workshop Item (Paper)

Uncontrolled Keywords:

Investments; User profile;Algorithmic decision making; Algorithmics; Counterfactuals; Decisions makings; Feature order; Generation method; State of the art; User feature; User's preferences; User's profiles;Decision making

Subjects:

Artificial Intelligence

Divisions:

Department of Artificial Intelligence

Depositing User:

Mr Nigam Prasad Bisoyi

Date Deposited:

16 Aug 2023 10:56

Last Modified:

16 Aug 2023 10:56

URI:

http://raiithold.iith.ac.in/id/eprint/11539