Prediction of Egg Price in Traditional Markets using Deep Learning

The agricultural sector, especially livestock, contributes significantly to the Indonesian economy. One of the many livestock products produced is chicken eggs. The problem for farmers is the uncertainty of selling prices, which exploitation by intermediaries causes. So, in solving this problem, information in the form of a prediction of the price of chicken eggs is needed to help farmers know the price before they sell them to the market. Predictions are made using deep learning algorithms, namely Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), which are evaluated using Root Mean Squared Error (RMSE), Mean Squared Error (MSE), Mean Absolute Error (MAE), and R Square to determine the performance of the two algorithms in predicting prices. This study uses data from April 2017 to December 2023 from the National Strategic Food Price Information Center (PIHPSN). Based on the experiments that have been carried out, the algorithm that is more dominant in making predictions is the GRU algorithm with the evaluation metric values of RMSE, MSE, MAE, and R Square in the Manis market, respectively of $0.034621,0.001199,0.022617$ and 0.952266. At the same time, the metric values in the market are $0.036574,0.001338,0.023991$, and 0.944691. With this research, the GRU algorithm is more dominant than LSTM.