Thailand Food Price Forecasting: Comparative Analysis of Machine Learning Models

This study aims to address food price fraud and predict pricing trends for key commodities-Cassava flour, Maize, Meat (chicken), and Rice-in Thailand, using advanced machine learning techniques to enhance forecasting accuracy and detect anomalies. We utilized historical food price data from 2000 to 2020 and incorporated USD exchange rate fluctuations to build and evaluate several regression models, including Linear Regression, Decision Tree Regressor, Random Forest Regressor, Gradient Boosting Regressor, and Support Vector Regressor. The Decision Tree and Random Forest models demonstrated superior performance with the lowest mean squared error (MSE) and root mean squared error (RMSE), effectively capturing price trends and fluctuations. In contrast, Linear Regression and Support Vector Regressor showed higher errors and less effectiveness in handling non-linear patterns. This study highlights the efficacy of machine learning in improving price prediction accuracy and detecting potential fraud, offering a robust framework for analyzing commodity pricing dynamics. The findings provide actionable insights for policymakers and stakeholders to implement proactive strategies, promoting greater market stability and fairness in Thailand's agricultural sector.