Evaluation of Software Effort Estimation Methods for Machine learning techniques

Abstract

Software development is a complicated process and includes a unique effort that Include many activities, resources, skills, and people to build a quality product. Thus, effort estimation is very important activity in scheduling of software project in order to deliver project on time and better effectively evaluate predictions. There are many models used in software effort estimation, including algorithmic, non-algorithmic, and machine learning models. This paper present a review of deferent machine learning methods that are using for effort estimation like regression models(liner regression ,decision trees, random forest ), neural networks , and then evaluate this models based on performance criteria such as MAE (Mean Absolute Error) and R2 Score. These models were tested on desharnias data using Python, The results were compared for the different models and gives notes on each model. It was found that the Random forest model is the best with deshanias data among the four models and achieved the highest score on the R SCORE scale, which amounted to 0.75

Keywords: Effort, Estimation ,Machine Learning , Neural Networks, Regression Models