Implementation of Artificial Neural Network (ANN) for Prediction of Tourist Arrivals in Pamoyanan Hill

Pamoyanan Hill is a popular hill tourist destination in Subang Regency and suitable for visitors of all ages. Unexpected fluctuations in the number of visitors can affect the income and development of this tourist attraction. This study aims to develop a prediction model for the number of tourist visits to Pamoyanan Hill using the Artificial Neural Network (ANN) method of the backpropagation algorithm. Implementation is carried out by dividing the data into training and testing data. The evaluation showed an average accuracy rate of 90.04% and an average error of 9.96%. The use of scenarios with a proportion of 80% training data and 20% testing provides optimal results. The ANN parameters used include: number of input neurons 2, number of hidden layers 10, number of outputs 1, alpha 0.01, and iterations of 1000. The activation function used is binary sigmoid. The parameters are set to achieve the best results, with a Mean Squared Error (MSE) of 0.02347103. Keywords