Citation

Haris, Mohammad and Chua, Fang Fang and Lim, Amy Hui Lan (2025) Expert-Integrated Stacking Model for Estimating Software Development Effort. In: 2025 IEEE International Conference on Computing (ICOCO), 06-08 October 2025, Kuching, Malaysia.

Text 23.pdf - Published Version Restricted to Repository staff only Download (963kB)

Abstract

Software providers are expected to deliver products on time, within budget, and in line with client expectations. Achieving this requires accurate effort estimation, which helps determine the necessary manpower, resources, timeline, and costs involved in software development. However, widely employed traditional "Software Development Effort Estimation (SDEE)" techniques are considered outdated, inflexible, and inaccurate due to the growing complexities of modern software. Expert estimation remains a pivotal traditional technique for exploiting human expertise, although relying entirely on this technique results in human bias and subjectivity. Machine Learning (ML) has recently acquired prominence to improve SDEE. Nonetheless, ML models based on a single algorithm may lead to suboptimal accuracy and be ineffective in handling a wide range of SDEE challenges. Besides, existing studies neglect human involvement and rely entirely on ML, which may overlook contextual factors and nuances that experts could provide based on their expertise and domain knowledge. This research proposes a novel stacking model, designated as EXpert-Integrated DiverSe-Bagging EnSembles Stacking for SoftwarE DEvelopment Effort Estimation (Xpert-S3E4). To develop, six diverse bagging ensembles are initially employed as base learners and integrate expert estimations to complement their estimations. Subsequently, "Feed-Forward Deep Neural Network (FFDNN)" is employed as a meta-model for the final SDEE. The Xpert-S3E4 model outperformed five existing SDEE models, achieving lower MSE, MAE, and RMSE and higher R2 across two diverse datasets, SEERA and USP05-FT.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	stacking, expert estimation, effort estimation
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science > QA76.75-76.765 Computer software
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	20 Apr 2026 03:51
Last Modified:	20 Apr 2026 03:51
URII:	http://shdl.mmu.edu.my/id/eprint/15777

Downloads

Edit (login required)