A Comparative Study for Effectiveness of Different Artificial Intelligence Models for Thai Lettuce Price Prediction

Abstract

Agriculture is one of the most important sectors in Thailand. Many farmers face challenges in crop pricing due to the fluctuation of the agricultural product market. Research on how to create an optimal crop portfolio suggests that accurate price predictions can help farmers choose the most profitable crops, thus solving this problem. In this research, we test different machine learning models, including Random Forest, XGBoost, and LSTM, to predict agricultural product, in this case Thai Lettuce prices. We use past price and meteorological data to train the models. The results show that LSTM performs better than the other models, achieving the lowest MSE (44.45), RMSE (6.67), and MAE (5.33). Additionally, LSTM provides a better fit to the data compared to Random Forest and XGBoost, which show lower predictive capabilities. These findings highlight LSTM's potential as a reliable model for agricultural price prediction, offering valuable insights to help farmers make better-informed decisions.