Toward Improving the Efficiency of Software Development Effort Estimation via Clustering Analysis

Abstract

Introduction:The precise estimation of software effort is a significant difficulty that project managers encounter during software development. Inaccurate forecasting leads to either overestimating or underestimating software effort, which can be detrimental for stakeholders. The International Function Point Users Group's Function Point Analysis (FPA) method is one of the most critical methods for software effort estimation. However, the practice of using the FPA method in the same fashion across all software areas needs to be reexamined. Aim: We propose a model for evaluating the influence of data clustering on software development effort estimation and then finding the best clustering method. We call this model the effort estimation using machine learning applied to the clusters (EEAC) model. Method: We cluster the dataset according to the clustering method and then apply the FPA and EEAC methods to these clusters for effort estimation. The clustering methods we use in this study include five categorical variable criteria (Development Platform, Industrial Sector, Language Type, Organization Type, and Relative Size) and the k-means clustering algorithm. Results: The experimental results show that the estimation accuracy obtaining with clustering consistently outperforms the accuracy without clustering for both the FPA and EEAC methods. Significantly, using the FPA method, the average improvement rate from using clustering as opposed to non-clustered was highest at 58.06%, according to the RMSE. With the EEAC method, this number reached 65.53%. The Industry Sector categorical variable achieves the best accuracy estimation compared to the other clustering criteria and k-means clustering. The improvement in accuracy in terms of the RMSE when applying this criterion is 63.68% for the FPA method and 72.02% for the EEAC method. Conclusion: Better results are obtained through dataset clustering compared to no clustering for both the FPA and EEAC methods. The Industry Sector is the most suitable clustering method among the tested clustering methods.

Strategic Integration of Artificial Intelligence for Sustainable Businesses: Implications for Data Management and Human User Engagement in the Digital Era

“…This research might have revealed variations in the level of AI awareness and acceptance within company employee culture, finding that investing in AI talent and skills positively influences AI adoption. Employee buy-in and readiness for AI-driven changes are vital, as was confirmed in [63]. Consequently, companies with a culture of curiosity and adaptability to change that fosters AI innovation are more likely to succeed in AI integration [64].…”

Manufacturing Cost Estimation Using Piecewise Function Approaches

“…As a downside, their work was limited to single linkage hierarchical clustering without the existence of ordinal and binary variables. Van Hai et al (2022) considered several alternative clustering methods to estimate effort (not cost) of software projects. They used five categorical variables and clustered using k-means, both for the variables collectively and separately to compare those approaches with not clustering the data.…”

Software Cost and Effort Estimation: Current Approaches and Future Trends

“…These methods have been used to increase the precision of cost and effort estimation [17]. The choice between these strategies depends on several variables, including the accessibility of data, the complexity of the project, and the expertise that is available inside the organization.…”