國立虎尾科技大學 |

Unraveling Biases and Customer Heterogeneity in E-Commerce Recommendation Systems.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Unraveling Biases and Customer Heterogeneity in E-Commerce Recommendation Systems./
作者:	Sharma, Sachin.
面頁冊數:	1 online resource (125 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
標題:	Judaic studies. -
電子資源:	click for full text (PQDT)
ISBN:	9798382746586

Unraveling Biases and Customer Heterogeneity in E-Commerce Recommendation Systems.
Sharma, Sachin.

Unraveling Biases and Customer Heterogeneity in E-Commerce Recommendation Systems. - 1 online resource (125 pages)

Source: Dissertations Abstracts International, Volume: 85-11, Section: B.

Thesis (D.B.A.)--University of Missouri - Saint Louis, 2024.

Includes bibliographical references

This research explores the biases present in AI algorithms within e-commerce recommendation systems, focusing on how these biases prioritize popular, sponsored, and private-label products over actual customer preferences. We extend the responsible AI discourse by critically examining these biases and their implications for fairness in e-commerce. To strengthen the current understanding of AI fairness in the fields of information systems and computer science, we aim to challenge the assumption that AI fairness is objective and the same for everyone. We examine how individual differences, such as equity sensitivity and exchange ideology, contribute to users' varied perceptions of AI fairness. Through a factorial design survey, we find that customers perceive popularity bias as less unfair than sponsored or private-label biases, indicating a possible preference for conformity or 'herd behavior.' Further, our findings support the influence of exchange ideology, as individuals with higher levels of this trait tend to view recommendation systems as more unfair. However, we did not find similar empirical support for equity sensitivity trait. Finally, we find that perceived fairness negatively influences distrust towards the recommendation systems. Our findings emphasize that addressing customer fairness perceptions is vital for mitigating distrust and enhancing the effectiveness of these systems. We conclude by discussing the theoretical contributions to the literature on AI and organizational justice and practical recommendations for improving the fairness of AI recommendation systems in e-commerce.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798382746586Subjects--Topical Terms:

1184516
Judaic studies.
Subjects--Index Terms:

Private-label biasesIndex Terms--Genre/Form:

554714
Electronic books.

Unraveling Biases and Customer Heterogeneity in E-Commerce Recommendation Systems.
LDR:03081ntm a22004217 4500 001 1148247
005 20240916070037.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382746586
035 $a (MiAaPQ)AAI31292696
035 $a AAI31292696
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Sharma, Sachin. $3 1474174
245 1 0 $a Unraveling Biases and Customer Heterogeneity in E-Commerce Recommendation Systems.
264 0 $c 2024
300 $a 1 online resource (125 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
500 $a Advisor: Singh, Vivek K.
502 $a Thesis (D.B.A.)--University of Missouri - Saint Louis, 2024.
504 $a Includes bibliographical references
520 $a This research explores the biases present in AI algorithms within e-commerce recommendation systems, focusing on how these biases prioritize popular, sponsored, and private-label products over actual customer preferences. We extend the responsible AI discourse by critically examining these biases and their implications for fairness in e-commerce. To strengthen the current understanding of AI fairness in the fields of information systems and computer science, we aim to challenge the assumption that AI fairness is objective and the same for everyone. We examine how individual differences, such as equity sensitivity and exchange ideology, contribute to users' varied perceptions of AI fairness. Through a factorial design survey, we find that customers perceive popularity bias as less unfair than sponsored or private-label biases, indicating a possible preference for conformity or 'herd behavior.' Further, our findings support the influence of exchange ideology, as individuals with higher levels of this trait tend to view recommendation systems as more unfair. However, we did not find similar empirical support for equity sensitivity trait. Finally, we find that perceived fairness negatively influences distrust towards the recommendation systems. Our findings emphasize that addressing customer fairness perceptions is vital for mitigating distrust and enhancing the effectiveness of these systems. We conclude by discussing the theoretical contributions to the literature on AI and organizational justice and practical recommendations for improving the fairness of AI recommendation systems in e-commerce.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Judaic studies. $3 1184516
650 4 $a Information technology. $3 559429
653 $a Private-label biases
653 $a AI algorithms
653 $a Exchange ideology
653 $a Perceived fairness
653 $a Recommendation systems
653 $a Equity sensitivity
655 7 $a Electronic books. $2 local $3 554714
690 $a 0489
690 $a 0800
690 $a 0751
690 $a 0454
710 2 $a University of Missouri - Saint Louis. $b College of Business Adminstration. $3 1474175
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 85-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31292696 $z click for full text (PQDT)