Employee performance assessment is a very important task that has to be performed by Human Resource Department in a certain institution, because it would be useful for the policy holders to help them making a decision in promoting or not their employees. This paper delivered the analysis of using Multi Layer Perceptron (MLP) to predict the performance of security unit personnels which has been trained by a formal institution. The data that was used in this research were collected from PT.

more »

... Merah Indonesia, that is a company that has role to train and to educate people who wants to be a security personnel. The data consist of 175 record with 10 attributes which include the assessment from aspects of cognitive, personality, and skill. MLP predicted the security personnel performances into three categories, i.e. "Good", "Enough", and "Fail". The 10 folds Cross Validation technique was also used in testing phase to measure its performance comprehensively with the output of the best accuracy was 97,75%.