Time Series Data Prediction using Elman Recurrent Neural Network on Tourist Visits in Tanah Lot Tourism Object
Putu Sugiartawan1, Sri Hartati2

1Putu Sugiartawan, Informatics Program, STMIK STIKOM Indonesia, Bali, Indonesia.
2Sri Hartati*, Department of Computer Science and Electronics Faculty of Mathematics and Natural Sciences, University Gadjah Mada, Yogyakarta, Indonesia.
Manuscript received on September 27, 2019. | Revised Manuscript received on October 30, 2019. | Manuscript published on October 30, 2019. | PP: 314-320 | Volume-9 Issue-1, October 2019 | Retrieval Number: A1833109119/2019©BEIESP | DOI: 10.35940/ijeat.A1833.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The prediction of time series data is a forecast using the analysis of a relationship pattern between what will be predicted (prediction) and the time variable. The prediction process using the recurrent neural network (RNN) model could recognize and learn the data pattern of time series, but the presence of fluctuations in data makes the introduction of data patterns difficult to be learned. The data used for forecasting are tourist visits to Tanah Lot Bali tourist attraction for 10 years (2008-2017). The training process uses the RNN method on high fluctuating data, which requires a relatively long time in recognizing and studying the data patterns. Modification of the RNN method on learning rate and momentum by using dynamic values, can shorten learning time. The results showed the learning time using the RNN dynamic value, smaller than the variants of the RNN method such as the RNN Elman, Jordan RNN, Fully RNN, LSTM and the feedforward method (Backpropagation). The resulting error value is 0,05105 MSE. This value is smaller than the Fully RNN, Jordan RNN, LSTM and Feedforward methods. The elman method has the shortest training time among other models. The purpose of this research is to make a prediction design consisting of sliding windows techniques, training with neural network models and validation of results with k-fold cross-validation.
Keywords: Time series, Recurrent neural network, k-fold cross validation, Sliding windows, Prediction.