Year: 2017
Type: article
Abstract: We study the problem of evaluation of different classification models that are used in machine learning. Thereason of the model evaluation is to find the optimal solution from various classification models generated in aniterated and complex model building process. Depending on the method of observing, there are different measuresfor evaluation the performance of the model. To evaluate classification models the most direct criterion that can bemeasured quantitatively is the classification accuracy. The main disadvantages of accuracy as a measure for evaluationare as follows: neglects the differences between the types of errors and it dependent on the distribution of class in thedataset. In this paper we discussed selection of the most appropriate measures depends on the characteristics of theproblem and the various ways it can be implemented.
Authors: Jasmina Dj. Novakovic, Alempije Veljovic, Sinisa S. Ilic, Zeljko Papic, Milica Tomovic, PE Post of Serbia
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W2586816396