EMPIRICAL VALIDATION OF RANDOM FOREST FOR AGILE SOFTWARE EFFORT ESTIMATION BASED ON STORY POINTS

Agile Software development has become famous in industries and replacing the traditional methods of software development. A correct estimation of effort in this concept still remains an argument in industries. Thus, the industry must be able to estimate the effort necessary for software development using agile methodology. For estimating effort different types of neural-networks Probabilistic Neural Network (PNN), General Regression Neural-Network (GRNN), Group Method of Data Handling (GMDH) Polynomial Neural-Network and Cascade-Correlation Neural-Network) are used. To achieve better prediction, effort estimation of agile projects researchers used Random Forest with Story Points Approach (SPA) in the place of neural-network because Random Forest is easy to implement and better than decision tree. Random Forest gives better results as compare to neural-network