Comparative technical analysis for Thai stock price prediction: a case study of food and beverage sector

This study conducts a comparative technical analysis of Thai stock price prediction within the food and beverage (F&B) sector, focusing on the performance of three machine learning algorithms: Support Vector Regression (SVR), Long Short-Term Memory (LSTM), and XGBoost. The results reveal significant performance variations among the models. LSTM demonstrates superior consistency and lower error metrics across all Thai F&B stocks. The study further evaluates the impact of using different sets of eight indicators versus three indicators on the predictive accuracy of the algorithms. While using more indicators usually improves model performance, LSTM benefits more from selecting specific technical indicators compared to SVR and XGBoost. Overall, this comparative analysis highlights the strengths and weaknesses of different machine learning algorithms in predicting Thai F&B stock prices, offering insights for improving forecasting models through optimized data usage and tailored approaches.