Forecasting smoked rubber sheets price based on a deep learning model with long short-term memory

<span>This research aimed to create suitable forecasting models with long-short term memory (LSTM) from time series data, the price of rubber smoked sheets (RSS3) using 2,631 data Rubber Authority Thailand for past 10 years. The was divided into two sets: first 2,105 points were used LSTM prediction model; second 526 estimate performance root mean square error (RMSE), absolute percentage (MAPE), and accuracy rate model. results showed that most model a total 9 layers comprised 3 primary LSTMs. Each layer has number neurons 100, 150, 200 obtain an optimal neural network technique. epochs iteration 30, 40, 50. Dropout between each have probability 30%. test measure 9-layer architecture gave best forecast, RMSE 2.4121, MAPE 0.0413 95.88% rate.</span>