Multicommodity Prices Prediction Using Multivariate Data-Driven Modeling: Indonesia Case

ABSTRACT

One of the problems experienced by micro, small, and medium enterprises (MSMEs) during this pandemic is that most MSME actors do not understand plan-making during a crisis. This situation was exacerbated by erratic commodity prices, which resulted in several MSME players choosing to temporarily close because their turnover got a drastic decline. To help MSME actors maintain their business by knowing commodity price predictions, we propose a deep learning model using the long short-term memory (LSTM) method to predict commodity prices in Indonesia. LSTM is a type of recurrent neural network (RNN) with a memory cell to store information and solve the vanishing gradient problem in RNN. Furthermore, multivariate LSTM leverages the model to predict datasets with more than one feature. This study used a dataset collected from the Pusat Informasi Harga Pangan Strategis Nasional (PIHPS Nasional) managed by the Indonesian Ministry of Finance and Bank Indonesia consisting of significantly contributed food commodities to the formation of (strategic) inflation rates in Indonesia. The time range of commodity prices is from August 1, 2017, to July 30, 2021. There are 11 commodity price features in the dataset, namely, rice, chicken meat, eggs, onions, garlic, large red chilies, curly red chilies, red chilies, green chilies, cooking oil, and sugar. The lowest mean absolute error (MAE) on prediction is up to 255.998 obtained by the attention multivariate LSTM model with the Adam optimizer, adding batch normalization (Batchnorm) layer, reducing LSTM layer, hidden size, and grouped features. It makes the prediction more accurate and avoids overfitting and underfitting in this case. IEEE