Recommender systems, consumer preferences, and anchoring effects

Gediminas Adomavicius, Jesse C Bockstedt, Shawn Curley, Jingjing Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

25 Citations (Scopus)

Abstract

Recommender systems are becoming a salient part of many e-commerce websites. Much research has focused on advancing recommendation technologies to improve the accuracy of predictions, while behavioral aspects of using recommender systems are often overlooked. In this study, we explore how consumer preferences at the time of consumption are impacted by predictions generated by recommender systems. We conducted three controlled laboratory experiments to explore the effects of system recommendations on preferences. Studies 1 and 2 investigated user preferences for television programs, which were surveyed immediately following program viewing. Study 3 broadened to an additional context-preferences for jokes. Results provide strong evidence viewers' preferences are malleable and can be significantly influenced by ratings provided by recommender systems. Additionally, the effects of pure number-based anchoring can be separated from the effects of the perceived reliability of a recommender system. Finally, the effect of anchoring is roughly continuous, operating over a range of perturbations of the system.

Original languageEnglish (US)
Title of host publicationCEUR Workshop Proceedings
Pages35-42
Number of pages8
Volume811
StatePublished - 2011
Externally publishedYes
EventJoint Workshop on Human Decision Making in Recommender Systems, Decisions@RecSys 2011 and User-Centric Evaluation of Recommender Systems and Their Interfaces-2, UCERSTI 2 - Affiliated with the 5th ACM Conference on Recommender Systems, RecSys 2011 - Chicago, IL, United States
Duration: Oct 23 2011Oct 26 2011

Other

OtherJoint Workshop on Human Decision Making in Recommender Systems, Decisions@RecSys 2011 and User-Centric Evaluation of Recommender Systems and Their Interfaces-2, UCERSTI 2 - Affiliated with the 5th ACM Conference on Recommender Systems, RecSys 2011
CountryUnited States
CityChicago, IL
Period10/23/1110/26/11

Fingerprint

Recommender systems
Television
Websites
Experiments

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Adomavicius, G., Bockstedt, J. C., Curley, S., & Zhang, J. (2011). Recommender systems, consumer preferences, and anchoring effects. In CEUR Workshop Proceedings (Vol. 811, pp. 35-42)

Recommender systems, consumer preferences, and anchoring effects. / Adomavicius, Gediminas; Bockstedt, Jesse C; Curley, Shawn; Zhang, Jingjing.

CEUR Workshop Proceedings. Vol. 811 2011. p. 35-42.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Adomavicius, G, Bockstedt, JC, Curley, S & Zhang, J 2011, Recommender systems, consumer preferences, and anchoring effects. in CEUR Workshop Proceedings. vol. 811, pp. 35-42, Joint Workshop on Human Decision Making in Recommender Systems, Decisions@RecSys 2011 and User-Centric Evaluation of Recommender Systems and Their Interfaces-2, UCERSTI 2 - Affiliated with the 5th ACM Conference on Recommender Systems, RecSys 2011, Chicago, IL, United States, 10/23/11.
Adomavicius G, Bockstedt JC, Curley S, Zhang J. Recommender systems, consumer preferences, and anchoring effects. In CEUR Workshop Proceedings. Vol. 811. 2011. p. 35-42
Adomavicius, Gediminas ; Bockstedt, Jesse C ; Curley, Shawn ; Zhang, Jingjing. / Recommender systems, consumer preferences, and anchoring effects. CEUR Workshop Proceedings. Vol. 811 2011. pp. 35-42
@inproceedings{f238945417ae4d798cad7d981186cbbd,
title = "Recommender systems, consumer preferences, and anchoring effects",
abstract = "Recommender systems are becoming a salient part of many e-commerce websites. Much research has focused on advancing recommendation technologies to improve the accuracy of predictions, while behavioral aspects of using recommender systems are often overlooked. In this study, we explore how consumer preferences at the time of consumption are impacted by predictions generated by recommender systems. We conducted three controlled laboratory experiments to explore the effects of system recommendations on preferences. Studies 1 and 2 investigated user preferences for television programs, which were surveyed immediately following program viewing. Study 3 broadened to an additional context-preferences for jokes. Results provide strong evidence viewers' preferences are malleable and can be significantly influenced by ratings provided by recommender systems. Additionally, the effects of pure number-based anchoring can be separated from the effects of the perceived reliability of a recommender system. Finally, the effect of anchoring is roughly continuous, operating over a range of perturbations of the system.",
author = "Gediminas Adomavicius and Bockstedt, {Jesse C} and Shawn Curley and Jingjing Zhang",
year = "2011",
language = "English (US)",
volume = "811",
pages = "35--42",
booktitle = "CEUR Workshop Proceedings",

}

TY - GEN

T1 - Recommender systems, consumer preferences, and anchoring effects

AU - Adomavicius, Gediminas

AU - Bockstedt, Jesse C

AU - Curley, Shawn

AU - Zhang, Jingjing

PY - 2011

Y1 - 2011

N2 - Recommender systems are becoming a salient part of many e-commerce websites. Much research has focused on advancing recommendation technologies to improve the accuracy of predictions, while behavioral aspects of using recommender systems are often overlooked. In this study, we explore how consumer preferences at the time of consumption are impacted by predictions generated by recommender systems. We conducted three controlled laboratory experiments to explore the effects of system recommendations on preferences. Studies 1 and 2 investigated user preferences for television programs, which were surveyed immediately following program viewing. Study 3 broadened to an additional context-preferences for jokes. Results provide strong evidence viewers' preferences are malleable and can be significantly influenced by ratings provided by recommender systems. Additionally, the effects of pure number-based anchoring can be separated from the effects of the perceived reliability of a recommender system. Finally, the effect of anchoring is roughly continuous, operating over a range of perturbations of the system.

AB - Recommender systems are becoming a salient part of many e-commerce websites. Much research has focused on advancing recommendation technologies to improve the accuracy of predictions, while behavioral aspects of using recommender systems are often overlooked. In this study, we explore how consumer preferences at the time of consumption are impacted by predictions generated by recommender systems. We conducted three controlled laboratory experiments to explore the effects of system recommendations on preferences. Studies 1 and 2 investigated user preferences for television programs, which were surveyed immediately following program viewing. Study 3 broadened to an additional context-preferences for jokes. Results provide strong evidence viewers' preferences are malleable and can be significantly influenced by ratings provided by recommender systems. Additionally, the effects of pure number-based anchoring can be separated from the effects of the perceived reliability of a recommender system. Finally, the effect of anchoring is roughly continuous, operating over a range of perturbations of the system.

UR - http://www.scopus.com/inward/record.url?scp=84891937816&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891937816&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84891937816

VL - 811

SP - 35

EP - 42

BT - CEUR Workshop Proceedings

ER -