Zero-Shot Learning for Accurate Project Duration Prediction in Crowdsourcing Software Development

Crowdsourcing Software Development (CSD) platforms, i.e., TopCoder, function as intermediaries connecting clients with developers. Despite employing systematic methodologies, these platforms frequently encounter high task abandonment rates, with approximately 19% of projects failing to meet satisfac...

Full description

Saved in:
Bibliographic Details
Main Authors: Tahir Rashid, Inam Illahi, Qasim Umer, Muhammad Arfan Jaffar, Waheed Yousuf Ramay, Hanadi Hakami
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Computers
Subjects:
Online Access:https://www.mdpi.com/2073-431X/13/10/266
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204923606597632
author Tahir Rashid
Inam Illahi
Qasim Umer
Muhammad Arfan Jaffar
Waheed Yousuf Ramay
Hanadi Hakami
author_facet Tahir Rashid
Inam Illahi
Qasim Umer
Muhammad Arfan Jaffar
Waheed Yousuf Ramay
Hanadi Hakami
author_sort Tahir Rashid
collection DOAJ
description Crowdsourcing Software Development (CSD) platforms, i.e., TopCoder, function as intermediaries connecting clients with developers. Despite employing systematic methodologies, these platforms frequently encounter high task abandonment rates, with approximately 19% of projects failing to meet satisfactory outcomes. Although existing research has focused on task scheduling, developer recommendations, and reward mechanisms, there has been insufficient attention to the support of platform moderators, or copilots, who are essential to project success. A critical responsibility of copilots is estimating project duration; however, manual predictions often lead to inconsistencies and delays. This paper introduces an innovative machine learning approach designed to automate the prediction of project duration on CSD platforms. Utilizing historical data from TopCoder, the proposed method extracts pertinent project attributes and preprocesses textual data through Natural Language Processing (NLP). Bidirectional Encoder Representations from Transformers (BERT) are employed to convert textual information into vectors, which are then analyzed using various machine learning algorithms. Zero-shot learning algorithms exhibit superior performance, with an average accuracy of 92.76%, precision of 92.76%, recall of 99.33%, and an f-measure of 95.93%. The implementation of the proposed automated duration prediction model is crucial for enhancing the success rate of crowdsourcing projects, optimizing resource allocation, managing budgets effectively, and improving stakeholder satisfaction.
format Article
id doaj-art-113ee2b6366a430a9dbf96cba2fa18ba
institution OA Journals
issn 2073-431X
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Computers
spelling doaj-art-113ee2b6366a430a9dbf96cba2fa18ba2025-08-20T02:11:12ZengMDPI AGComputers2073-431X2024-10-01131026610.3390/computers13100266Zero-Shot Learning for Accurate Project Duration Prediction in Crowdsourcing Software DevelopmentTahir Rashid0Inam Illahi1Qasim Umer2Muhammad Arfan Jaffar3Waheed Yousuf Ramay4Hanadi Hakami5Department of Computer Science, The Superior University, Lahore 54000, PakistanDepartment of Computing and Emerging Technologies, Emerson University, Multan 60000, PakistanDepartment of Computer Sciences, COMSATS University Islamabad, Vehari 61000, PakistanDepartment of Computer Science, The Superior University, Lahore 54000, PakistanDepartment of Computer Science, Cholistan University of Veterinary and Animal Sciences, Bahawalpur 63100, PakistanDepartment of Software Engineering, College of Engineering, University of Business and Technology, Jeddah 21361, Saudi ArabiaCrowdsourcing Software Development (CSD) platforms, i.e., TopCoder, function as intermediaries connecting clients with developers. Despite employing systematic methodologies, these platforms frequently encounter high task abandonment rates, with approximately 19% of projects failing to meet satisfactory outcomes. Although existing research has focused on task scheduling, developer recommendations, and reward mechanisms, there has been insufficient attention to the support of platform moderators, or copilots, who are essential to project success. A critical responsibility of copilots is estimating project duration; however, manual predictions often lead to inconsistencies and delays. This paper introduces an innovative machine learning approach designed to automate the prediction of project duration on CSD platforms. Utilizing historical data from TopCoder, the proposed method extracts pertinent project attributes and preprocesses textual data through Natural Language Processing (NLP). Bidirectional Encoder Representations from Transformers (BERT) are employed to convert textual information into vectors, which are then analyzed using various machine learning algorithms. Zero-shot learning algorithms exhibit superior performance, with an average accuracy of 92.76%, precision of 92.76%, recall of 99.33%, and an f-measure of 95.93%. The implementation of the proposed automated duration prediction model is crucial for enhancing the success rate of crowdsourcing projects, optimizing resource allocation, managing budgets effectively, and improving stakeholder satisfaction.https://www.mdpi.com/2073-431X/13/10/266classificationBERTmachine learningcrowdsourcingcrowdsourcing software developmentTopCoder
spellingShingle Tahir Rashid
Inam Illahi
Qasim Umer
Muhammad Arfan Jaffar
Waheed Yousuf Ramay
Hanadi Hakami
Zero-Shot Learning for Accurate Project Duration Prediction in Crowdsourcing Software Development
Computers
classification
BERT
machine learning
crowdsourcing
crowdsourcing software development
TopCoder
title Zero-Shot Learning for Accurate Project Duration Prediction in Crowdsourcing Software Development
title_full Zero-Shot Learning for Accurate Project Duration Prediction in Crowdsourcing Software Development
title_fullStr Zero-Shot Learning for Accurate Project Duration Prediction in Crowdsourcing Software Development
title_full_unstemmed Zero-Shot Learning for Accurate Project Duration Prediction in Crowdsourcing Software Development
title_short Zero-Shot Learning for Accurate Project Duration Prediction in Crowdsourcing Software Development
title_sort zero shot learning for accurate project duration prediction in crowdsourcing software development
topic classification
BERT
machine learning
crowdsourcing
crowdsourcing software development
TopCoder
url https://www.mdpi.com/2073-431X/13/10/266
work_keys_str_mv AT tahirrashid zeroshotlearningforaccurateprojectdurationpredictionincrowdsourcingsoftwaredevelopment
AT inamillahi zeroshotlearningforaccurateprojectdurationpredictionincrowdsourcingsoftwaredevelopment
AT qasimumer zeroshotlearningforaccurateprojectdurationpredictionincrowdsourcingsoftwaredevelopment
AT muhammadarfanjaffar zeroshotlearningforaccurateprojectdurationpredictionincrowdsourcingsoftwaredevelopment
AT waheedyousuframay zeroshotlearningforaccurateprojectdurationpredictionincrowdsourcingsoftwaredevelopment
AT hanadihakami zeroshotlearningforaccurateprojectdurationpredictionincrowdsourcingsoftwaredevelopment