The Application of the Multi-Layer Perceptron Neural Network Technique for Developing the Career-Suggestion Simulation Model for Undergraduate Students
The goal of the study is to develop the career-suggestion simulation model for newly graduated students with a bachelor’s degree in information technology by using the Multi-Layer Perceptron Neural Network technique. Due to the lack of data collected for developing the model from a limited data sets, the researcher decided to apply the Resample technique to solve the problem of the data set with imbalanced prediction outputs by adjusting the imbalance of the data set starting from 100% to 500%. Subsequently, the Multi-Layer Perceptron Neural Network technique was applied for developing the career-suggestion simulation model. There were two approaches used for testing the effectiveness of the simulation model, including the 5-fold cross validation and 10-fold cross validation techniques. The results of the simulation model’s effectiveness test using the 10-fold cross validation technique with the adjusted resample of 500% and the Multi-Layer Perceptron Neural Network technique provide the accuracy of 93.62% which is higher than the career-suggestion simulation model which applies the Multi-Layer Perceptron Neural Network technique alone. The research findings reveal that the simulation model can be used as the prototype of the career-suggestion simulation model for newly graduated students with a bachelor’s degree in information technology.
Keywords: Model, Resample, Multi-Layer Perceptron Neural Network.