D.T. Wiyanti, I. Kharisudin, A.B. Setiawan, A.K. Nugroho
Numerous top algorithms for time series prediction issues have been proposed. Time-series prediction has stirred up wide attention in many research fields because it is an important direction of dynamic data analysis and processing. The prediction is used in a variety of practical situations, especially for the pressing demand for forecasting future data trends based on historical information. While demand forecasting remains a challenge, developments in machine-learning have provided dramatic improvements. In this article, we investigate the feasibility and comparative analysis of Deep Learning approaches to forecasting the demand problem with implementation to a public dataset. We use comparison with RMSE performance metrics to analyze the Deep Learning performance better than other model techniques, including Random Forest, Gradient Boosted Trees, and Support Vector Machine. However, the forecasting problem is a vital need for business decision making. © Published under licence by IOP Publishing Ltd.
Mathematics Department, Faculty of Mathematics and Natural Science, Universitas Negeri Semarang, Indonesia; Economics Science Department, Faculty of Economics, Universitas Negeri Semarang, Indonesia; Informatics Engineering Department, Universitas Jenderal Soedirman, Indonesia
