Agent-Based Modeling of Context Effects in Consumer Choice

Jarod Vanderlynden, Philippe Mathieu and Romain Warlop ()
Additional contact information
Jarod Vanderlynden: Université de Lille, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 - Centrale Lille - Université de Lille - CNRS - Centre National de la Recherche Scientifique, SMAC - Systèmes Multi-Agents et Comportements - CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 - Centrale Lille - Université de Lille - CNRS - Centre National de la Recherche Scientifique
Philippe Mathieu: Université de Lille, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 - Centrale Lille - Université de Lille - CNRS - Centre National de la Recherche Scientifique, SMAC - Systèmes Multi-Agents et Comportements - CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 - Centrale Lille - Université de Lille - CNRS - Centre National de la Recherche Scientifique
Romain Warlop: 55 - Fifty-five

Post-Print from HAL

Abstract: This paper presents an agent-based model that explains three major context effects: decoy, similarity, and compromise effects, commonly observed in consumer decision-making. The model uses loss aversion theory, using a utility function that evaluates products relative to a reference point, defined by the average price and quality of all competing options. Agents are characterized by varying sensitivities to price and quality. Rather than forecasting exact consumer numbers, the model simulates relative preferences within a fixed population, making it a robust tool for analyzing market share dynamics. It accurately reproduces key behavioral phenomena and is calibrated using real-world retail data. Practical applications include price optimization and forecasting the impact of new product introductions. This framework offers a powerful yet focused tool for marketers seeking to understand and leverage consumers behaviors in competitive environments.

Date: 2025-10-25
Note: View the original document on HAL open archive server: https://hal.science/hal-05344092v1
References: View references in EconPapers View complete reference list from CitEc
Citations:

Published in 28th European Conference on Artificial Intelligence, Oct 2025, Bologna, Italy. pp.3622 - 3629, ⟨10.3233/FAIA251239⟩

Downloads: (external link)
https://hal.science/hal-05344092v1/document (application/pdf)

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-05344092

DOI: 10.3233/FAIA251239

Access Statistics for this paper

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