Technological development makes the need to exchange accurate information based on data stored in a database is needed. Data mining itself is one of the techniques to find information and hidden knowledge from a data. One algorithm that is quite widely used in the data mining classification process is naïve bayes, chosen because it has a relatively short time, simple and has high accuracy. Naïve Bayes algorithm has a weakness which is the probability cannot measure the accuracy of a prediction. Therefore, a particle swarm optimization (PSO) method is needed. This study applies PSO to improve the performance of the naïve bayes algorithm where the PSO measurement parameter lies in its performance effectiveness against naïve bayes. The method used is experiment by using 7 cases of different datasets which are divided into 2 tests. Naïve Bayes and naïve Bayes tests are based on PSO (NB-PSO) wherein the NB-PSO test uses 2 parameters of inertia weight and population size with a total of 6 repetitions. The results of the experiments carried out showed that the effectiveness of the use of the optimization method. From 7 datasets used, 3 of them were able to increase the accuracy value with an average of 0.33% with the PSO success rate of all data reached only 42.68%.

27/11/2018

978-602-53524-0-9

© The authors.
This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/

479 times.