Particle Swarm Optimization for Predicting the Development Effort of Software Projects

Abstract

Software project planning includes as one of its main activities software development effort prediction (SDEP). Effort (measured in person-hours) is useful to budget and bidding the projects. It corresponds to one of the variables most predicted, actually, hundreds of studies on SDEP have been published. Therefore, we propose the application of the Particle Swarm Optimization (PSO) metaheuristic for optimizing the parameters of statistical regression equations (SRE) applied to SDEP. Our proposal incorporates two elements in PSO: the selection of the SDEP model, and the automatic adjustment of its parameters. The prediction accuracy of the SRE optimized through PSO (PSO-SRE) was compared to that of a SRE model. These models were trained and tested using eight data sets of new and enhancement software projects obtained from an international public repository of projects. Results based on statistically significance showed that the PSO-SRE was better than the SRE in six data sets at 99% of confidence, in one data set at 95%, and statistically equal than SRE in the remaining data set. We can conclude that the PSO can be used for optimizing SDEP equations taking into account the type of development, development platform, and programming language type of the projects.

MFLion‐DMN: Mayfly Lion‐optimized deep maxout network for prediction of software development effort

“…• In Alanis-Tamez et al, 15 PSO-SRE is utilized for optimizing the attributes utilized in software development effort prediction, but it did not apply other metaheuristics to optimize attributes for the SRE.…”

“…However, this method did not generate improved accuracy. Alanis‐Tamez et al 15 devise a technique of PSO to optimize the attributes of Statistical Regression Equations (SRE) adapted to predict the software development efforts. The method combined two attributes in PSO wherein the first is the selection of the software development prediction effort model and the second was the adjustment of its attributes.…”

“…The issues confronted by classical software development effort prediction methodologies are described below: In Alanis‐Tamez et al, 15 PSO‐SRE is utilized for optimizing the attributes utilized in software development effort prediction, but it did not apply other metaheuristics to optimize attributes for the SRE. In Amazal and Idri, 16 the database quality influences the estimated accuracy and technique applicability. As analogy‐based techniques adapt historical data to devise their predictions, enhanced performance is attained whenever source and target projects are the same, but whenever the difference between the historical and target projects expands, the outcomes become inadequate. Hybrid Wavelet Neural Network (WNN) is devised in Kaushik and Singal 18 to predict the effort, but it failed to combine WNN with metaheuristic models to forecast the software effort in the agile platform of software design. The key issue confronted by the Ensemble‐based method 19 is devised for predicting the effort, but it failed to adapt the optimization methods' design at the project portfolio level. The need for tremendously consistent and precise software development effort estimation in software engineering is a complex standpoint and needs strategic planning.…”