<![CDATA[K-Nearest Neighbor (KNN) is a method that belongs to the group in classifying data that is simple and easy to implement, effective on larger data, and can classify data appropriately. One of the advantages possessed by the K-Nearest Neighbor algorithm is that it can be applied to large amounts of data and has a lot of noise so this method is quite easy to implement. This study aims to utilize the advantages of the K-NN algorithm in data-based classification to increase efficiency and accuracy in the employee selection process in determining suitable employee candidates by the criteria determined by the company. The results showed that the results of employee presets received from 21 testing data were 51% and for employee presentations that failed as much as 49% while from the entire data set of 140 data, the accuracy level produced after being tested using rapid miner tools resulted in 82% accuracy. So it can be concluded that the percentage accuracy of 82% shows that most prospective employees have been predicted or classified correctly by the model. This high level of accuracy can be an indication that the K-Nearest Neighbor method used in combination with Rapidminer can handle prospective employee data well.]]>
Copyrights © 2024
