Analysis and Prediction of Foodstuffs Prices in Tasikmalaya Using ELM and LSTM

Abstract

Foodstuffs price analysis and prediction is one of the important research topics. This paper applies Long Short-Term Memory (LSTM) and Extreme Learning Machines (ELM) as models for forecasting the price of rice, chicken meat, chicken egg, shallot, garlic, and red chili in the Tasikmalaya traditional market. The dataset is a daily time series obtained from April 2017 - February 2023. LSTM models perform accurately to forecast 5 foodstuffs prices and obtain MAPE scores of no more than 3%. ELM works well to predict the price of rice, chicken meat, chicken egg, shallot, and garlic with MAPE scores are less than 1%. The price of rice, chicken egg, shallot, and red chili has an increasing trend. The correlation analysis finds that the price of chicken egg, shallot, and red chili has a positive correlation with each other.