A Framework for Optimal Crowdsourcing Contest Design

Wangsheng Zhu; Jiahui Mo; Sumit Sarkar; Syam Menon

A Framework for Optimal Crowdsourcing Contest Design

Wangsheng Zhu, Jiahui Mo, Sumit Sarkar, Syam Menon

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

Abstract

Crowdsourcing contests are popular mechanisms for firms to obtain solutions to tasks from external sources. Platforms allow firms to decide the attributes of their contests, such as prize and duration. Selecting an appropriate set of attributes can increase the probability of success. We develop a framework that identifies an effective prediction model, and maximizes the predicted probability of success of a crowdsourcing contest using optimization techniques. The framework considers design features of a focal task as also those of other open tasks competing with the focal task. The contest design problem is formulated as a mixed linear knapsack problem, with several novel variants. We present solution procedures for these variants, and validate the framework using a real-world dataset. Our results show that the contest designs recommended by the proposed framework can increase success probabilities significantly relative to what seekers specify.

Original language	English
Title of host publication	42nd International Conference on Information Systems, ICIS 2021 TREOs
Subtitle of host publication	"Building Sustainability and Resilience with IS: A Call for Action"
Publisher	Association for Information Systems
ISBN (Electronic)	9781713893608
Publication status	Published - 2021
Externally published	Yes
Event	42nd International Conference on Information Systems: Building Sustainability and Resilience with IS: A Call for Action, ICIS 2021 TREOs - Austin, United States Duration: 12 Dec 2021 → 15 Dec 2021

Publication series

Name	42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action"

Conference

Conference	42nd International Conference on Information Systems: Building Sustainability and Resilience with IS: A Call for Action, ICIS 2021 TREOs
Country/Territory	United States
City	Austin
Period	12/12/21 → 15/12/21

Bibliographical note

Publisher Copyright:
© 2021 42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action". All Rights Reserved.

Keywords

Success probability
mixed linear knapsack problem
optimization
prediction model

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Cite this

Zhu, W., Mo, J., Sarkar, S., & Menon, S. (2021). A Framework for Optimal Crowdsourcing Contest Design. In 42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action" (42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action"). Association for Information Systems.

Zhu, Wangsheng ; Mo, Jiahui ; Sarkar, Sumit et al. / A Framework for Optimal Crowdsourcing Contest Design. 42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action". Association for Information Systems, 2021. (42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action").

@inproceedings{c0a5bc81fd214e1e8ededc18aa92c4c6,

title = "A Framework for Optimal Crowdsourcing Contest Design",

abstract = "Crowdsourcing contests are popular mechanisms for firms to obtain solutions to tasks from external sources. Platforms allow firms to decide the attributes of their contests, such as prize and duration. Selecting an appropriate set of attributes can increase the probability of success. We develop a framework that identifies an effective prediction model, and maximizes the predicted probability of success of a crowdsourcing contest using optimization techniques. The framework considers design features of a focal task as also those of other open tasks competing with the focal task. The contest design problem is formulated as a mixed linear knapsack problem, with several novel variants. We present solution procedures for these variants, and validate the framework using a real-world dataset. Our results show that the contest designs recommended by the proposed framework can increase success probabilities significantly relative to what seekers specify.",

keywords = "Success probability, mixed linear knapsack problem, optimization, prediction model",

author = "Wangsheng Zhu and Jiahui Mo and Sumit Sarkar and Syam Menon",

note = "Publisher Copyright: {\textcopyright} 2021 42nd International Conference on Information Systems, ICIS 2021 TREOs: {"}Building Sustainability and Resilience with IS: A Call for Action{"}. All Rights Reserved.; 42nd International Conference on Information Systems: Building Sustainability and Resilience with IS: A Call for Action, ICIS 2021 TREOs ; Conference date: 12-12-2021 Through 15-12-2021",

year = "2021",

language = "English",

series = "42nd International Conference on Information Systems, ICIS 2021 TREOs: {"}Building Sustainability and Resilience with IS: A Call for Action{"}",

publisher = "Association for Information Systems",

booktitle = "42nd International Conference on Information Systems, ICIS 2021 TREOs",

}

Zhu, W, Mo, J, Sarkar, S & Menon, S 2021, A Framework for Optimal Crowdsourcing Contest Design. in 42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action". 42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action", Association for Information Systems, 42nd International Conference on Information Systems: Building Sustainability and Resilience with IS: A Call for Action, ICIS 2021 TREOs, Austin, United States, 12/12/21.

A Framework for Optimal Crowdsourcing Contest Design. / Zhu, Wangsheng; Mo, Jiahui; Sarkar, Sumit et al.
42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action". Association for Information Systems, 2021. (42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action").

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - A Framework for Optimal Crowdsourcing Contest Design

AU - Zhu, Wangsheng

AU - Mo, Jiahui

AU - Sarkar, Sumit

AU - Menon, Syam

PY - 2021

Y1 - 2021

N2 - Crowdsourcing contests are popular mechanisms for firms to obtain solutions to tasks from external sources. Platforms allow firms to decide the attributes of their contests, such as prize and duration. Selecting an appropriate set of attributes can increase the probability of success. We develop a framework that identifies an effective prediction model, and maximizes the predicted probability of success of a crowdsourcing contest using optimization techniques. The framework considers design features of a focal task as also those of other open tasks competing with the focal task. The contest design problem is formulated as a mixed linear knapsack problem, with several novel variants. We present solution procedures for these variants, and validate the framework using a real-world dataset. Our results show that the contest designs recommended by the proposed framework can increase success probabilities significantly relative to what seekers specify.

AB - Crowdsourcing contests are popular mechanisms for firms to obtain solutions to tasks from external sources. Platforms allow firms to decide the attributes of their contests, such as prize and duration. Selecting an appropriate set of attributes can increase the probability of success. We develop a framework that identifies an effective prediction model, and maximizes the predicted probability of success of a crowdsourcing contest using optimization techniques. The framework considers design features of a focal task as also those of other open tasks competing with the focal task. The contest design problem is formulated as a mixed linear knapsack problem, with several novel variants. We present solution procedures for these variants, and validate the framework using a real-world dataset. Our results show that the contest designs recommended by the proposed framework can increase success probabilities significantly relative to what seekers specify.

KW - Success probability

KW - mixed linear knapsack problem

KW - optimization

KW - prediction model

UR - https://www.scopus.com/pages/publications/85192361450

M3 - Conference Paper published in a book

AN - SCOPUS:85192361450

T3 - 42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action"

BT - 42nd International Conference on Information Systems, ICIS 2021 TREOs

PB - Association for Information Systems

T2 - 42nd International Conference on Information Systems: Building Sustainability and Resilience with IS: A Call for Action, ICIS 2021 TREOs

Y2 - 12 December 2021 through 15 December 2021

ER -

Zhu W, Mo J, Sarkar S, Menon S. A Framework for Optimal Crowdsourcing Contest Design. In 42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action". Association for Information Systems. 2021. (42nd International Conference on Information Systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action").

A Framework for Optimal Crowdsourcing Contest Design

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Other files and links

Fingerprint

Cite this