Download This PaperComparative Analysis on Prediction of Software Effort Estimation Using Machine Learning Techniques
6 Pages Posted: 8 Jul 2020
Date Written: April 1, 2020
Abstract
Effort Estimation (EE) is a technique for finding the entire effort required to predict the accuracy of a model. It’s a significant chore in software application development practice. To find accurate estimation, numerous predictive models have developed in recent times. The estimate prepared during the early stage of a model expansion is inaccurate since requirements at that time are not very clear, but as the model progresses, the accuracy of the estimation increases. Therefore, accurate estimation is essential to choose for each software application model development. Here, Linear Regression (LR), Multi-layer perceptron (MLP), Random Forest (RF) algorithms are implemented using WEKA toolkit, and results shows that Linear Regression shows better estimation accuracy than Multilayer Perceptron and Random Forest.
Keywords: Effort Estimation, Machine Learning Techniques, Prediction, Classification, Random Forest, Linear Regression, Multi-layer perceptron
Suggested Citation: Suggested Citation