Ensemble Learning for Crowdfunding Dynamics: JingDong Crowdfunding Projects

Hu Min; Kaihan Wu; Minghao Tan; Junyan Lin; Yufan Zheng; Choujun Zhan

doi:10.1007/978-981-19-6135-9_28

Ensemble Learning for Crowdfunding Dynamics: JingDong Crowdfunding Projects

Hu Min, Kaihan Wu^*, Minghao Tan, Junyan Lin, Yufan Zheng, Choujun Zhan^*

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

As an emerging internet financing model with high efficiency, low cost, diversified returns, and a small investment, crowdfunding is sought after by entrepreneurs and investors. However, many crowdfunding projects are faced with the risk of low success rates and failure to reach the financing target within the specified period. Therefore, the prediction of crowdfunding project financing results and multi-model comparison are important ways to improve the project success rates and reduce market risk. First, we collected project data of JingDong (JD) crowdfunding platform for preprocessing and analyzed the characteristics of successful projects. Then, we use ensemble learning and traditional machine learning models to predict the daily amount of crowdfunding with grid search to obtain the optimal hyperparameters of each model. Several evaluation metrics are then employed to assess the performance of the model.The experimental results demonstrate that the Extra Tree Regression (ETR) ensemble model achieves the best prediction performance, with a coefficient of determination(R²) of 90.1%, when forecasting the daily crowdfunding fundraising. Furthermore, the ensemble learning model showed significant advantages in other evaluation indicators, indicating its potential in forecasting the financing amount of crowdfunding projects. © 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Original language	English
Title of host publication	Neural Computing for Advanced Applications - Third International Conference, NCAA 2022
Subtitle of host publication	Proceedings
Editors	Haijun Zhang, Yuehui Chen, Xianghua Chu, Zhao Zhang, Tianyong Hao, Zhou Wu, Yimin Yang
Publisher	Springer Singapore
Pages	372-386
Number of pages	15
Volume	Part II
ISBN (Electronic)	9789811961359
ISBN (Print)	9789811961342
DOIs	https://doi.org/10.1007/978-981-19-6135-9_28
Publication status	Published - 2022
Externally published	Yes
Event	3rd International Conference on Neural Computing for Advanced Applications (NCAA 2022) - University of Jinan, Jinan, China Duration: 8 Jul 2022 → 10 Jul 2022 https://dl2link.com/ncaa2022/

Publication series

Name	Communications in Computer and Information Science
Volume	1638
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	3rd International Conference on Neural Computing for Advanced Applications (NCAA 2022)
Abbreviated title	2022 NCAA
Place	China
City	Jinan
Period	8/07/22 → 10/07/22
Internet address	https://dl2link.com/ncaa2022/

Research Keywords

Correlation coefficient
Crowdfunding financing prediction
Extra Tree Regression
Grid search

Access Output

10.1007/978-981-19-6135-9_28

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Min, H., Wu, K., Tan, M., Lin, J., Zheng, Y., & Zhan, C. (2022). Ensemble Learning for Crowdfunding Dynamics: JingDong Crowdfunding Projects. In H. Zhang, Y. Chen, X. Chu, Z. Zhang, T. Hao, Z. Wu, & Y. Yang (Eds.), Neural Computing for Advanced Applications - Third International Conference, NCAA 2022: Proceedings (Vol. Part II, pp. 372-386). (Communications in Computer and Information Science; Vol. 1638). Springer Singapore. https://doi.org/10.1007/978-981-19-6135-9_28

Min, Hu ; Wu, Kaihan ; Tan, Minghao et al. / Ensemble Learning for Crowdfunding Dynamics : JingDong Crowdfunding Projects. Neural Computing for Advanced Applications - Third International Conference, NCAA 2022: Proceedings. editor / Haijun Zhang ; Yuehui Chen ; Xianghua Chu ; Zhao Zhang ; Tianyong Hao ; Zhou Wu ; Yimin Yang. Vol. Part II Springer Singapore, 2022. pp. 372-386 (Communications in Computer and Information Science).

@inproceedings{c5ad973b8b844d47ba9d5419e442cb5e,

title = "Ensemble Learning for Crowdfunding Dynamics: JingDong Crowdfunding Projects",

abstract = "As an emerging internet financing model with high efficiency, low cost, diversified returns, and a small investment, crowdfunding is sought after by entrepreneurs and investors. However, many crowdfunding projects are faced with the risk of low success rates and failure to reach the financing target within the specified period. Therefore, the prediction of crowdfunding project financing results and multi-model comparison are important ways to improve the project success rates and reduce market risk. First, we collected project data of JingDong (JD) crowdfunding platform for preprocessing and analyzed the characteristics of successful projects. Then, we use ensemble learning and traditional machine learning models to predict the daily amount of crowdfunding with grid search to obtain the optimal hyperparameters of each model. Several evaluation metrics are then employed to assess the performance of the model.The experimental results demonstrate that the Extra Tree Regression (ETR) ensemble model achieves the best prediction performance, with a coefficient of determination(R2) of 90.1%, when forecasting the daily crowdfunding fundraising. Furthermore, the ensemble learning model showed significant advantages in other evaluation indicators, indicating its potential in forecasting the financing amount of crowdfunding projects. {\textcopyright} 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.",

keywords = "Correlation coefficient, Crowdfunding financing prediction, Extra Tree Regression, Grid search",

author = "Hu Min and Kaihan Wu and Minghao Tan and Junyan Lin and Yufan Zheng and Choujun Zhan",

year = "2022",

doi = "10.1007/978-981-19-6135-9_28",

language = "English",

isbn = "9789811961342",

volume = "Part II",

series = "Communications in Computer and Information Science",

publisher = "Springer Singapore",

pages = "372--386",

editor = "Haijun Zhang and Yuehui Chen and Xianghua Chu and Zhao Zhang and Tianyong Hao and Zhou Wu and Yimin Yang",

booktitle = "Neural Computing for Advanced Applications - Third International Conference, NCAA 2022",

address = "Singapore",

note = "3rd International Conference on Neural Computing for Advanced Applications (NCAA 2022), 2022 NCAA ; Conference date: 08-07-2022 Through 10-07-2022",

url = "https://dl2link.com/ncaa2022/",

}

Min, H, Wu, K, Tan, M, Lin, J, Zheng, Y & Zhan, C 2022, Ensemble Learning for Crowdfunding Dynamics: JingDong Crowdfunding Projects. in H Zhang, Y Chen, X Chu, Z Zhang, T Hao, Z Wu & Y Yang (eds), Neural Computing for Advanced Applications - Third International Conference, NCAA 2022: Proceedings. vol. Part II, Communications in Computer and Information Science, vol. 1638, Springer Singapore, pp. 372-386, 3rd International Conference on Neural Computing for Advanced Applications (NCAA 2022), Jinan, China, 8/07/22. https://doi.org/10.1007/978-981-19-6135-9_28

Ensemble Learning for Crowdfunding Dynamics: JingDong Crowdfunding Projects. / Min, Hu; Wu, Kaihan; Tan, Minghao et al.
Neural Computing for Advanced Applications - Third International Conference, NCAA 2022: Proceedings. ed. / Haijun Zhang; Yuehui Chen; Xianghua Chu; Zhao Zhang; Tianyong Hao; Zhou Wu; Yimin Yang. Vol. Part II Springer Singapore, 2022. p. 372-386 (Communications in Computer and Information Science; Vol. 1638).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Ensemble Learning for Crowdfunding Dynamics

T2 - 3rd International Conference on Neural Computing for Advanced Applications (NCAA 2022)

AU - Min, Hu

AU - Wu, Kaihan

AU - Tan, Minghao

AU - Lin, Junyan

AU - Zheng, Yufan

AU - Zhan, Choujun

PY - 2022

Y1 - 2022

N2 - As an emerging internet financing model with high efficiency, low cost, diversified returns, and a small investment, crowdfunding is sought after by entrepreneurs and investors. However, many crowdfunding projects are faced with the risk of low success rates and failure to reach the financing target within the specified period. Therefore, the prediction of crowdfunding project financing results and multi-model comparison are important ways to improve the project success rates and reduce market risk. First, we collected project data of JingDong (JD) crowdfunding platform for preprocessing and analyzed the characteristics of successful projects. Then, we use ensemble learning and traditional machine learning models to predict the daily amount of crowdfunding with grid search to obtain the optimal hyperparameters of each model. Several evaluation metrics are then employed to assess the performance of the model.The experimental results demonstrate that the Extra Tree Regression (ETR) ensemble model achieves the best prediction performance, with a coefficient of determination(R2) of 90.1%, when forecasting the daily crowdfunding fundraising. Furthermore, the ensemble learning model showed significant advantages in other evaluation indicators, indicating its potential in forecasting the financing amount of crowdfunding projects. © 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

AB - As an emerging internet financing model with high efficiency, low cost, diversified returns, and a small investment, crowdfunding is sought after by entrepreneurs and investors. However, many crowdfunding projects are faced with the risk of low success rates and failure to reach the financing target within the specified period. Therefore, the prediction of crowdfunding project financing results and multi-model comparison are important ways to improve the project success rates and reduce market risk. First, we collected project data of JingDong (JD) crowdfunding platform for preprocessing and analyzed the characteristics of successful projects. Then, we use ensemble learning and traditional machine learning models to predict the daily amount of crowdfunding with grid search to obtain the optimal hyperparameters of each model. Several evaluation metrics are then employed to assess the performance of the model.The experimental results demonstrate that the Extra Tree Regression (ETR) ensemble model achieves the best prediction performance, with a coefficient of determination(R2) of 90.1%, when forecasting the daily crowdfunding fundraising. Furthermore, the ensemble learning model showed significant advantages in other evaluation indicators, indicating its potential in forecasting the financing amount of crowdfunding projects. © 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

KW - Correlation coefficient

KW - Crowdfunding financing prediction

KW - Extra Tree Regression

KW - Grid search

UR - http://www.scopus.com/inward/record.url?scp=85142688439&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85142688439&origin=recordpage

U2 - 10.1007/978-981-19-6135-9_28

DO - 10.1007/978-981-19-6135-9_28

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9789811961342

VL - Part II

T3 - Communications in Computer and Information Science

SP - 372

EP - 386

BT - Neural Computing for Advanced Applications - Third International Conference, NCAA 2022

A2 - Zhang, Haijun

A2 - Chen, Yuehui

A2 - Chu, Xianghua

A2 - Zhang, Zhao

A2 - Hao, Tianyong

A2 - Wu, Zhou

A2 - Yang, Yimin

PB - Springer Singapore

Y2 - 8 July 2022 through 10 July 2022

ER -

Min H, Wu K, Tan M, Lin J, Zheng Y, Zhan C. Ensemble Learning for Crowdfunding Dynamics: JingDong Crowdfunding Projects. In Zhang H, Chen Y, Chu X, Zhang Z, Hao T, Wu Z, Yang Y, editors, Neural Computing for Advanced Applications - Third International Conference, NCAA 2022: Proceedings. Vol. Part II. Springer Singapore. 2022. p. 372-386. (Communications in Computer and Information Science). Epub 2022 Oct 21. doi: 10.1007/978-981-19-6135-9_28