Towards incorporating ethics in recommendation systems

Christine Balagué () and El Mehdi Rochd ()
Additional contact information
Christine Balagué: IMT-BS - MMS - Département Management, Marketing et Stratégie - TEM - Télécom Ecole de Management - IMT - Institut Mines-Télécom [Paris] - IMT-BS - Institut Mines-Télécom Business School - IMT - Institut Mines-Télécom [Paris], LITEM - Laboratoire en Innovation, Technologies, Economie et Management (EA 7363) - UEVE - Université d'Évry-Val-d'Essonne - IMT-BS - Institut Mines-Télécom Business School - IMT - Institut Mines-Télécom [Paris]
El Mehdi Rochd: IMT-BS - MMS - Département Management, Marketing et Stratégie - TEM - Télécom Ecole de Management - IMT - Institut Mines-Télécom [Paris] - IMT-BS - Institut Mines-Télécom Business School - IMT - Institut Mines-Télécom [Paris]

Post-Print from HAL

Abstract: Most of product recommender systems are based on artificial intelligence algorithms using machine learning or deep learning techniques. One of the current challenges is to avoid negative effects of these product recommender systems on customers (or prospects), such as unfairness, biais, discrimination, opacity, encapsulated opinion in the implemented recommender systems algorithms. This paper is about the challenge of fairness. We define the concept and present some measures of fairness. Next, we will present a new predictive model, to which we plan to incorporate equity criteria. Using a dataset from the entertainment industry, we measure the fairness for each method and compare the results.

Keywords: Ethique; Intelligence artificielle; Responsabilité; Algorithmes (search for similar items in EconPapers)
Date: 2019-04-08
References: Add references at CitEc
Citations:

Published in Séminaire Technologies et IA Responsables. Chaire Good In Tech, Apr 2019, Paris, France

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-02093828

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().