METRICS FOR EVALUATING MACHINE LEARNING MODEL – A REVIEW

Abstract

In classical software engineering, software must be verified and validated properly in order to ensure the quality and making software bug free. Software Testing is done through well-established methodology Software Testing Life Cycle like Unit testing, Integration testing, System testing and Regression testing etc. Similarly, In Machine Learning Model is developed for particular problem such as Classifiers, predictive model, Clustering model etc. in order to validate the model it is important to calculate various metric through which once can choose the best model. As same model can develop by using various algorithms. This paper reviews the metrics for evaluating the model and their accuracy.