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

DESCRIPTION

Achieving our goals requires establishing a dialogue between experts in information science and consumer science. On the one hand, data scientists need to develop algorithms to identify consumer preferences and generate recommendations. On the other hand, behavioral economists need to design controlled experiments based on principles established in cognitive psychology and behavioral economics. These efforts enable us to develop theories on how people make choices when assisted by decision-making algorithms and to measure acceptability. These two groups have been collaborating to build on each other’s expertise and conduct large-scale testing through platform and plug-in development. We have been collecting data and metadata to conduct a robust assessment of the impact of algorithmic decisions on individuals and society. To achieve this, we have designed and deployed large-scale experiments to observe consumer behavior in a controlled environment. These deployments are being conducted and tested in accordance with new definitions of satisfaction and adoption metrics, as well as the development of algorithms, tools, and novel human-centric approaches to data exploration and analysis.

ACTIVITIES

This document summarizes our activities and the resulting challenges. During the first year, we organized three meetings during which we planned our activities 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.

A list of our publications is available here, as well as a glossary that we have developed to enable collaboration among 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), September 2021, Linz, 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 (online), 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 Improving Crowd Worker Performance. 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, June 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 October 14, 2026
Updated on October 14, 2026