Contextual Recommendations in Action - Bridging AI and Real-Life Economics

DESCRIPTION

Achieving our action requires to establish of a dialogue between experts in information sciences and consumer sciences. On the one hand, data scientists need to develop algorithms to reveal consumer preferences and produce recommendations. On the other hand, behavior economists need to design deployments controlled experiences according to principles established in cognitive psychology and behavioral economics. These efforts enable to develop theories on how people make choices when assisted by decision-making algorithms and to measure acceptability. These two parties have been working together to feed off each other and deploy large-scale testing through platform and plug-in development. We have been collecting data and metadata to conduct a robust measurement of the impact of algorithmic decisions on individuals and on society. To achieve that, we have designed and deployed large-scale experiments for the observation of consumption of behaviors in a controlled environment. These deployments are being conducted and tested according to new definitions of satisfaction and adoption measures, and of course the development of algorithms, tools and novel human-centric data exploration and analysis approaches.

ACTIVITIES

This document summarizes our action and the resulting challenges. During the first year, we organized three meetings during which we designed our experiences on AdAnalyst, developed a methodology for deploying experiences and modeling preferences, and obtained the necessary authorizations from Data Protection Officers and analyzed the risks associated with GDPR.

The list of our publications is available here, as well as a lexicon that we have developed to allow us to work together between computer scientists, economists and lawyers.
We have also contributed to the Digital Platforms and Algorithmic Risks working group as part of the GdR Internet et Société: https://cis.cnrs.fr/plateformes-et-risques-algorithmiques/

SELECTED LIST OF PUBLICATIONS

  • Abdelouahab Chibah, Sihem Amer−Yahia, Laure Berti−Equille. QeNoBi: A System for QuErying and miNing BehavIoral Patterns Authors' Copy. 2021 IEEE 37th International Conference on Data Engineering (ICDE), Apr 2021, Chania, France. pp.2673−2676, ;10.1109/ICDE51399.2021.00301t. 

  • Anes Bendimerad, Marc Plantevit, Céline Robardet, Sihem Amer−Yahia. User−driven geolocated event detection in social media. IEEE Transactions on Knowledge and Data Engineering, Institute of Electrical and Electronics Engineers, In press, 33 (2), pp.796−809. ;10.1109/TKDE.2019.2931340t. 

  • Behrooz Omidvar−Tehrani, Sihem Amer−Yahia. User Group Analytics Survey and Research Opportunities. IEEE Transactions on Knowledge and Data Engineering, Institute of Electrical and Electronics Engineers, 2020, ;10.1109/TKDE.2019.2913651t.

  • Bruno Brandoli, Gabriel Spadon, Travis Esau, Patrick Hennessy, Andre Carvalho, et al.. DropLeaf: a precision farming smartphone application for measuring pesticide spraying methods. Journal of Computers and Electronics in Agriculture, Elsevier, 2020. 

  • Dong Wei, Senjuti Basu Roy, Sihem Amer−Yahia. Recommending Deployment Strategies for Collaborative Tasks. SIGMOD/PODS '20: International Conference on Management of Data, 2020, Portland (virtual), United States. pp.3−17, ;10.1145/3318464.3389719t. 

  • Fabian Colque Zegarra, Juan Carbajal Ipenza, Behrooz Omidvar−Tehrani, Viviane Moreira, Sihem Amer−Yahia, et al.. Visual exploration of rating datasets and user groups. Future Generation Computer Systems, Elsevier, 2020, 105, pp.547−561.;
    10.1016/j.future.2019.12.011t. 

  • Idir Benouaret, Mohamed Bouadi, Sihem Amer−Yahia. Multi−Objective Recommendations and Promotions at TOTAL. The 32nd International Conference on Database and Expert Systems Applications (DEXA2021), Sep 2021, Lintz, Austria. 

  • Idir Benouaret, Sihem Amer−Yahia, Senjuti Basu Roy, Christiane Kamdem−Kengne, Jalil Chagraoui. Enabling Decision Support Through Ranking and Summarization of Association Rules for TOTAL Customers. Transactions on Large−Scale Data− and Knowledge−Centered Systems, Springer Berlin / Heidelberg, 2020, pp.160−193. ; 10.1007/978−3−662−62271−1_6t. 

  • Jose Rodrigues−Jr, Marco Gutierrez, Gabriel Spadon, Bruno Brandoli, Sihem Amer−Yahia. LIG−Doctor: efficient patient trajectory prediction using Bidirectional Minimal Gated−Recurrent Networks. Information sciences, Information Sciences, 2021, ;10.1016/j.ins.2020.09.024t. 

  • Mariia Seleznova, Behrooz Omidvar−Tehrani, Sihem Amer−Yahia, Eric Simon. Guided exploration of user groups. Proceedings of the VLDB Endowment (PVLDB), VLDB Endowment, 2020, 13 (9), pp.1469−1482. ;10.14778/3397230.3397242t.

  • Mohammadreza Esfandiari, Ria Mae Borromeo, Sepideh Nikookar, Paras Sakharkar, Sihem Amer−Yahia, et al.. Multi−Session Diversity to Improve User Satisfaction in Web Applications. WWW '21: The Web Conference 2021, Apr 2021, Ljubljana Slovenia, France. pp.1928−1936, ;10.1145/3442381.3450046t. 

  • Sandrine da Col, Radu Ciucanu, Marta Soare, Nassim Bouarour, Sihem Amer−Yahia. DashBot: An ML−Guided Dashboard Generation System Authors' Copy. 30th ACM International Conference on Information and Knowledge Management, Nov 2021, Queensland (in line), Australia. 

  • Senjuti Basu Roy, Lei Chen, Atsuyuki Morishima, James Monedero, Pierre Bourhis, et al.. Making AI Machines Work for Humans in FoW. SIGMOD record, ACM, 2020, 49 (2), pp.30−35. ;10.1145/3442322.3442327t. 

  • Sihem Amer−Yahia, Aurélien Personnaz, Laure Berti−Equille. Dora the explorer: Exploring Very Large Data with Interactive Deep Reinforcement Learning Authors' Copy. 30th ACM International Conference on Information and Knowledge Management, Nov 2021, Queensland, Australia. 

  • Sihem Amer−Yahia, Laure Berti−Equille, Abdelouahab Chibah. A Framework for Statistically−Sound Customer Segment Search Authors' Copy. The 8th IEEE International Conference on Data Science and Advanced Analytics, Oct 2021, Porto (virtual), Portugal. 

  • Sihem Amer−Yahia, Masaki Matsubara, Ria Borromeo. Task Assignment Strategies for Crowd Worker Ability Improvement. The 24th ACM Conference on Computer−Supported Cooperative Work and Social Computing, Oct 2021, Virtual, France. 

  • Sihem Amer−Yahia, Reynold Cheng, Mohamed Bouadi, Abdelouahab Chibah, Mohammadreza Esfandiari, et al.. An ML−Powered Human Behavior Management System. Bulletin of the Technical Committee on Data Engineering, IEEE Computer Society, 2020, 43 (3), pp.53−64. 

  • Sihem Amer−Yahia, Senjuti Basu Roy. Data Management to Social Science and Back in the Future of Work. SIGMOD/PODS '21: International Conference on Management of Data, Jun 2021, Virtual Event China, France. pp.2876−2877, ;10.1145/3448016.3457536t. 

  • Sihem Amer−Yahia, Shady Elbassuoni, Ahmad Ghizzawi, Anas Hosami. Quantifying and Addressing Ranking Disparity in Human−Powered Data Acquisition. KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Aug 2021, Virtual Event Singapore, France. pp.2525−2533, ;10.1145/3447548.3467063t. 

  • Sihem Amer−Yahia, Shady Elbassuoni, Ahmad Ghizzawi, Ria Borromeo, Emilie Hoareau, et al.. Fairness in Online Jobs: {A} Case Study on TaskRabbit and Google. International Conference on Extending Database Technologies (EDBT), 2020, Copenhagen, Denmark. ;10.5441/002/edbt.2020.62t. 

  • Sihem Amer−Yahia, Shady Elbassuoni, Ahmad Ghizzawi. Fairness of Scoring in Online Job Marketplaces. ACM/IMS Transactions on Data Science, ACM, 2020, 1 (4), pp.1−30. ;10.1145/3402883t. 

  • Sihem Amer−Yahia, Shady Elbassuoni, Behrooz Omidvar−Tehrani, Ria Borromeo, Mehrdad Farokhnejad. GroupTravel: Customizing Travel Packages for Groups. International Conference on Extending Database Technologies, 2020, Lisbon, Portugal. ;10.5441/002/edbt.2019.13t. 

  • Sihem Amer−Yahia, Tova Milo, Brit Youngmann. Exploring Ratings in Subjective Databases. SIGMOD/PODS '21: International Conference on Management of Data, Apr 2021, Virtual Event China, France. pp.62−75, ;10.1145/3448016.3457259t. 

  • Sihem Amer−Yahia, Tova Milo, Brit Youngmann. SubDEx: Exploring Ratings in Subjective Databases (Authors' Copy). 2021 IEEE 37th International Conference on Data Engineering (ICDE), Apr 2021, Chania, France. pp.2653−2656, ;10.1109/ICDE51399.2021.00296t.

Published on  January 11, 2024
Updated on January 11, 2024