Designing Decision Support System for Scholarship Prediction Using Adaptive Neuro Fuzzy Inference System Algorithm

Abstract

The increasing enthusiasm of students applying for scholarships caused the selection committee to experience difficulties in the decision-making process, the large and complex amount of data caused the committee to need a system that could assist in the decision making process. One method in the system that can help in decision making is artificial neural networks. This method is capable of reasoning like the human brain's brain network to solve a problem into a form of neurons or equations as a basis for determining a solution or prediction. Researchers have done the method of artificial neural network using the Backpropagation method with an accuracy of 0.9090 and MAE 0.0001017 on the epoch to 329. Based on these results the researchers want to make improvements using a new method, namely adaptive neuro fuzzy inference system (ANFIS) and yields an accuracy value of 92.04% and Mean Absolute Error (MAE) of 0.0001001 on the epoch to 318. The test results were obtained using 3000 data through the K-3 Fold Validation test and 0.2 learning rate configuration and 0.2 momentum.