Prediksi Kunjungan Wisatawan Ke Indonesia Dengan Reduksi Noise Pada Mesin Pencari Menggunakan Metode Hilbert Huang Transform


 In many studies, Google Trends Data is efficient to analyze and estimate as explanatory variables, including tourism predictions. However, data retrieval are always plagued by noise. Without noise processing, the predictive ability of search engine may be weak, even invalid. As a processing method, Hilbert-Huang Transform (HHT) can reduce or clean Forecasting art science predicting future events. LSTM able overcome long-term dependence. This study tries provide predictions tourist visits in engines using method. The forecasting architecture that built composed 3 hidden layers with 100 units neurons nerves function process information, which layer also becomes input layer. Prediction test results on dataset 156 rows, resulting RMSE values 2019 getting 129249 results, HHT + 653058. so closer remembering 0.