Analyzing the Effect of Variables in the Software Development Effort Estimation

Velarde, Hector; Santiesteban, Cosme; García, Ana María Ruiz-Ruano; Casillas, Jorge

doi:10.1109/tla.2016.7786366

Cited by 4 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study adopts an extreme learning algorithm to predict software design efforts. Similar work can also be seen by Velarde et al (2016). The variability in the cost variables is identified in the context of Source Lines of Codes (SLOC), function points analysis, and feature engineering tasks.…”

Section: Introductionmentioning

confidence: 83%

Software Development Effort Estimation Using Relational Database and Optimized Learning Mechanism

Nagarajappa,

Suresh

2023

Journal of Computer Science

View full text Add to dashboard Cite

Accurately estimating the cost of software development is crucial for effective project planning and resource allocation. However, traditional cost estimation methods rely heavily on expert judgment and historical data, which can be time consuming and prone to errors. This study suggests a learning-based cost estimation model that leverages relational databases to improve accuracy. The proposed approach estimates project cost based on the effort required to complete software development, which is a key driver of the project cost. The proposed model is designed to address the challenges posed by the variability in open-source development, including variable team sizes, working hours, and expertise. The study collects and pre-processes data from open-source platforms and selects cost drivers and metrics based on logical rules and SQL queries. Moreover, we propose an optimized Artificial Neural Network (ANN) with augmented topology to automate the selection of neuron units, layers, and adjustment of learnable parameters according to the input variables. The proposed model is evaluated on a 100 open-source software repositories dataset and demonstrates its effectiveness in accurately estimating development cost. The system is implemented using Python and evaluated using performance parameters such as MSE, RMSE, MAE, and MMRE. Results indicate that our proposed model offers a more accurate and efficient approach to software cost estimation, especially for freelancers and outsourcing firms. The proposed model has the potential to save time and resources and improve the reliability and accuracy of software cost estimation.

show abstract

Section: Introductionmentioning

confidence: 83%