• Aucun résultat trouvé

Towards using responsible artificial intelligence in product recommender systems in marketing

N/A
N/A
Info
Télécharger
Protected

Academic year: 2021

Partager "Towards using responsible artificial intelligence in product recommender systems in marketing"

Copied!
2
0
0

Chargement.... (Voir le texte intégral maintenant)

Texte intégral

(1)

HAL Id: hal-02332033

https://hal.archives-ouvertes.fr/hal-02332033

Submitted on 24 Oct 2019

HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers.

L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

Towards using responsible artificial intelligence in

product recommender systems in marketing

Christine Balagué, El Mehdi Rochd

To cite this version:

Christine Balagué, El Mehdi Rochd. Towards using responsible artificial intelligence in product rec-ommender systems in marketing. 41st Annual ISMS Marketing Science Conference, Jun 2019, Rome, Italy. �hal-02332033�

(2)

TOWARDS USING RESPONSIBLE ARTIFICIAL INTELLIGENCE IN

PRODUCT RECOMMENDER SYSTEMS IN MARKETING

Abstract :

Most of product recommender systems in marketing are based on artificial intelligence algorithms using machine learning or deep learning techniques. One of the current challenges for companies 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 research focuses on the fairness challenge. We first make a literature review on the importance and challenges of using ethical algorithms. Second, we define the fairness concept and present the reasons why it is important for companies to address this issue in marketing. Third, we present the different methodologies used in recommender systems algorithms. Using a dataset in the entertainment industry, we measure the algorithm fairness for each methology and compare the results. Finally, we improve the existing methods by proposing a new product recommender system aiming at increasing fairness versus previous methods, without compromising the

recommendation systems performance.

Keywords: recommender systems, algorithms, responsibility, ethics

Authors: Christine BALAGUE, El Mehdi ROCHD, LITEM, Univ Evry, Institut

Mines-Télécom Business School, Université Paris-Saclay, 91025, Evry, France.

Références

Télécharger maintenant ( PDF - 2 Page - 634.93 KB )

Documents relatifs

Towards Flexible Assistive Robots Using Artificial Intelligence

Thus, the control architecture of a GiraffPlus-like assistive robot must continu- ously process sensor data to understand the status of a person (according to his/her

Capturing Data in the Presence of Noise for Artificial Intelligence Systems

As mentioned above, this finding may have particular utility in specific circumstances; where a noisy ranking environment is present, making a comparison does not increase the noise,

Comparing Prediction Models for Active Learning in Recommender Systems

As the main challenge in applying active learning for recommender systems is that users are not willing to answer many queries in order to rate the queried items, we evaluate AM and

Recommender Systems for Product Bundling

We evaluated: (i) The personal demand function by using a validation set in order to test the predicted alphas compared to the actual alphas, using the RMSE measure,

Improved Questionnaire Trees for Active Learning in Recommender Systems

Using active learning to build adaptive questionnaire trees is the promising ap- proach to address the cold-start problem in recommender systems6. The per- formance of

Affective Recommender Systems: the Role of Emotions in Recommender Systems

We identified four main areas where further research should be conducted in order to build true a↵ective recommender systems: (i) using emotions as context in the entry stage,

Towards Ranking in Folksonomies for Personalized Recommender Systems in E-Learning

The impact of the various semantic infor- mation sources will be evaluated by considering several variants of the ranking algorithm, thereby showing which context features

Using Images in Context-Aware Recommender Systems

Thus, existing recommender systems do not model explicitly user long-term needs that related to the visual appearance of products expressed as “like product X of look-and-feel Y”..