Open AccessComparative analysis of Machine learning and Deep learning algorithms for Software Effort Estimation
Author(s) -
A. G. Priya Varshini,
Anitha Kumari K,
D. Janani,
Soundariya R.S.
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1767/1/012019
Subject(s) - machine learning , computer science , artificial intelligence , random forest , mean squared error , robustness (evolution) , software , task (project management) , algorithm , support vector machine , data mining , mathematics , statistics , engineering , biochemistry , chemistry , systems engineering , gene , programming language
Artificial Intelligence is a superset of Machine Learning and Deep learning, used to build intelligent systems that can solve problems. Software Effort Estimation is used to predict the number of hours of work required to complete the task. It is difficult and a challenging task to forecast Software Effort in the project during initial stages, due to several uncertainties. Software Effort Estimation helps in planning, scheduling, budgeting a project. Various experiments were proposed to predict effort alike expert judgment, analogy based estimations, regression estimations, classification approaches, deep learning algorithms. In this paper, comparison of deepnet, neuralnet, support vector machine and random forest algorithms were carried out and the results show that random forest outperforms other algorithms because of its robustness and capacity to handle large datasets. Evaluation metrics deliberated are Mean Absolute Error, Root Mean Squared Error, Mean Square Error and R-Squared.