Success Prediction of Crowdsourced Projects for Competitive Crowdsourced Software Development

Competitive Crowdsourcing Software Development (CCSD) is popular among academics and industries because of its cost-effectiveness, reliability, and quality. However, CCSD is in its early stages and does not resolve major issues, including having a low solution submission rate and high project failur...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences Vol. 14; no. 2; p. 489
Main Authors: Rashid, Tahir, Anwar, Shumaila, Jaffar, Muhammad Arfan, Hakami, Hanadi, Baashirah, Rania, Umer, Qasim
Format: Journal Article
Language:English
Published: Basel MDPI AG 01.01.2024
Subjects:
BERT
classification
Competition
Competitive Crowdsourced Software Development (CCSD)
Crowdsourcing
Deep learning
Pilots and pilotage
Software
Software development
Success factors
TopCoder
Workers
Germany
ISSN:2076-3417, 2076-3417
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Competitive Crowdsourcing Software Development (CCSD) is popular among academics and industries because of its cost-effectiveness, reliability, and quality. However, CCSD is in its early stages and does not resolve major issues, including having a low solution submission rate and high project failure risk. Software development wastes stakeholders’ time and effort as they cannot find a suitable solution in a highly dynamic and competitive marketplace. It is, therefore, crucial to automatically predict the success of an upcoming software project before crowdsourcing it. This will save stakeholders’ and co-pilots’ time and effort. To this end, this paper proposes a well-known deep learning model called Bidirectional Encoder Representations from Transformers (BERT) for the success prediction of Crowdsourced Software Projects (CSPs). The proposed model is trained and tested using the history data of CSPs collected from TopCoder using its REST API. The outcomes of hold-out validation indicate a notable enhancement in the proposed approach compared to existing methods, with increases of 13.46%, 8.83%, and 11.13% in precision, recall, and F1 score, respectively.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2076-3417
2076-3417
DOI:10.3390/app14020489