Models for Predicting Development Effort of Website Development Projects

Effort estimation is a process of predicting probable cost and development time of a software. Estimating software development effort remains a complex problem, and the one which continues to draw significant research attention. Correctness in estimating the required software development effort plays a critical factor in the success of software project management. For good software estimation model the estimated effort should be close to the actual effort. Accurate estimation allows manager to allocate the resources to plan and coordinate all activities. Several techniques like neural network, fuzzy logic, genetic engineering and regression techniques are used either individually or in combination as hybrid approaches to predict the effort. Web-based software projects are different than conventional projects, and hence the task of estimation for these projects is a complex one. In this paper, we present linear regression, nonlinear regression and neural network prediction models. The case in point is website development projects, around 36 website development projects rendered by postgraduate students in supervised academic setting vaguely mimicking the industry scenario are considered for model development. The models were evaluated for their prediction accuracy through mean absolute error, mean magnitude of relative error, mean of magnitude of error relative to the estimate (MMER) and root mean square error for each project in both verification and validation phase. Out of 36 development projects successfully completed by postgraduate students, 26 were used for the development and 10 were used for verification of the models. Evaluations of the models have shown MMER of 0.01301, 0.03405 and 0.048551, respectively, for multiple liner regression, nonlinear regression and neural network models during verification. The marginal difference in error estimates have indicated that all models can be fittingly used for effort computation-specific applicability to website development projects.