Dynamic Sliding Window Model for Service Reputation

Xin Zhou, Toru Ishida, Yohei Murakami

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

3 Citations (Scopus)

Abstract

Reputation plays a crucial role in the success of e-commerce. In a commercial transaction, it is necessary to present reputation values of web services in a timely and a robust manner so as to counter the unfair ratings of malicious users. To address the time lag problem, most popular web sites use an averaging algorithm with fixed sliding windows, window size is constant and older ratings are dropped upon the arrival of new ratings. Herein, we propose a dynamic sliding window model that is capable of reflecting the reputation values yielded by the latest changes in services. Furthermore, we implement a statistical strategy to filter out unfair ratings by calculating the standard deviation of the ratings after transposing the two-dimensional linear window into the constant one-dimensional window by using linear regression. Experiments confirm the effectiveness of the proposed model, it outperforms the existing reputation system by 40% on average based on the 5 test cases examined, and also show that it can asymptotically converge to the underlying reputation value as ratings accumulate.

Original languageEnglish
Title of host publicationProceedings - 2015 IEEE International Conference on Services Computing, SCC 2015
EditorsWu Chou, Paul P. Maglio, Incheon Paik
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages25-32
Number of pages8
ISBN (Electronic)9781467372817
DOIs
Publication statusPublished - 2015 Aug 17
Externally publishedYes
EventIEEE International Conference on Services Computing, SCC 2015 - New York, United States
Duration: 2015 Jun 272015 Jul 2

Publication series

NameProceedings - 2015 IEEE International Conference on Services Computing, SCC 2015

Conference

ConferenceIEEE International Conference on Services Computing, SCC 2015
CountryUnited States
CityNew York
Period15/6/2715/7/2

Fingerprint

Linear regression
Web services
Websites
Experiments

Keywords

  • Dynamic sliding window model
  • Reputation system
  • Time lag
  • Unfair rating

ASJC Scopus subject areas

  • Information Systems
  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Zhou, X., Ishida, T., & Murakami, Y. (2015). Dynamic Sliding Window Model for Service Reputation. In W. Chou, P. P. Maglio, & I. Paik (Eds.), Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015 (pp. 25-32). [7207332] (Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SCC.2015.14

Dynamic Sliding Window Model for Service Reputation. / Zhou, Xin; Ishida, Toru; Murakami, Yohei.

Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015. ed. / Wu Chou; Paul P. Maglio; Incheon Paik. Institute of Electrical and Electronics Engineers Inc., 2015. p. 25-32 7207332 (Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015).

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

Zhou, X, Ishida, T & Murakami, Y 2015, Dynamic Sliding Window Model for Service Reputation. in W Chou, PP Maglio & I Paik (eds), Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015., 7207332, Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015, Institute of Electrical and Electronics Engineers Inc., pp. 25-32, IEEE International Conference on Services Computing, SCC 2015, New York, United States, 15/6/27. https://doi.org/10.1109/SCC.2015.14
Zhou X, Ishida T, Murakami Y. Dynamic Sliding Window Model for Service Reputation. In Chou W, Maglio PP, Paik I, editors, Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 25-32. 7207332. (Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015). https://doi.org/10.1109/SCC.2015.14
Zhou, Xin ; Ishida, Toru ; Murakami, Yohei. / Dynamic Sliding Window Model for Service Reputation. Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015. editor / Wu Chou ; Paul P. Maglio ; Incheon Paik. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 25-32 (Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015).
@inproceedings{ac79ac263ad04cc09035a7ae9f0af62d,
title = "Dynamic Sliding Window Model for Service Reputation",
abstract = "Reputation plays a crucial role in the success of e-commerce. In a commercial transaction, it is necessary to present reputation values of web services in a timely and a robust manner so as to counter the unfair ratings of malicious users. To address the time lag problem, most popular web sites use an averaging algorithm with fixed sliding windows, window size is constant and older ratings are dropped upon the arrival of new ratings. Herein, we propose a dynamic sliding window model that is capable of reflecting the reputation values yielded by the latest changes in services. Furthermore, we implement a statistical strategy to filter out unfair ratings by calculating the standard deviation of the ratings after transposing the two-dimensional linear window into the constant one-dimensional window by using linear regression. Experiments confirm the effectiveness of the proposed model, it outperforms the existing reputation system by 40{\%} on average based on the 5 test cases examined, and also show that it can asymptotically converge to the underlying reputation value as ratings accumulate.",
keywords = "Dynamic sliding window model, Reputation system, Time lag, Unfair rating",
author = "Xin Zhou and Toru Ishida and Yohei Murakami",
year = "2015",
month = "8",
day = "17",
doi = "10.1109/SCC.2015.14",
language = "English",
series = "Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "25--32",
editor = "Wu Chou and Maglio, {Paul P.} and Incheon Paik",
booktitle = "Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015",

}

TY - GEN

T1 - Dynamic Sliding Window Model for Service Reputation

AU - Zhou, Xin

AU - Ishida, Toru

AU - Murakami, Yohei

PY - 2015/8/17

Y1 - 2015/8/17

N2 - Reputation plays a crucial role in the success of e-commerce. In a commercial transaction, it is necessary to present reputation values of web services in a timely and a robust manner so as to counter the unfair ratings of malicious users. To address the time lag problem, most popular web sites use an averaging algorithm with fixed sliding windows, window size is constant and older ratings are dropped upon the arrival of new ratings. Herein, we propose a dynamic sliding window model that is capable of reflecting the reputation values yielded by the latest changes in services. Furthermore, we implement a statistical strategy to filter out unfair ratings by calculating the standard deviation of the ratings after transposing the two-dimensional linear window into the constant one-dimensional window by using linear regression. Experiments confirm the effectiveness of the proposed model, it outperforms the existing reputation system by 40% on average based on the 5 test cases examined, and also show that it can asymptotically converge to the underlying reputation value as ratings accumulate.

AB - Reputation plays a crucial role in the success of e-commerce. In a commercial transaction, it is necessary to present reputation values of web services in a timely and a robust manner so as to counter the unfair ratings of malicious users. To address the time lag problem, most popular web sites use an averaging algorithm with fixed sliding windows, window size is constant and older ratings are dropped upon the arrival of new ratings. Herein, we propose a dynamic sliding window model that is capable of reflecting the reputation values yielded by the latest changes in services. Furthermore, we implement a statistical strategy to filter out unfair ratings by calculating the standard deviation of the ratings after transposing the two-dimensional linear window into the constant one-dimensional window by using linear regression. Experiments confirm the effectiveness of the proposed model, it outperforms the existing reputation system by 40% on average based on the 5 test cases examined, and also show that it can asymptotically converge to the underlying reputation value as ratings accumulate.

KW - Dynamic sliding window model

KW - Reputation system

KW - Time lag

KW - Unfair rating

UR - http://www.scopus.com/inward/record.url?scp=84953397996&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84953397996&partnerID=8YFLogxK

U2 - 10.1109/SCC.2015.14

DO - 10.1109/SCC.2015.14

M3 - Conference contribution

T3 - Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015

SP - 25

EP - 32

BT - Proceedings - 2015 IEEE International Conference on Services Computing, SCC 2015

A2 - Chou, Wu

A2 - Maglio, Paul P.

A2 - Paik, Incheon

PB - Institute of Electrical and Electronics Engineers Inc.

ER -