Stock price prediction is traditionally considered a critical task in finance and investment sectors, where accurate forecasting models are supposed to provide significant economic advantages both for investors and analysts. In this work, we explore the application of Support Vector Regression (SVR) and Artificial Neural Networks (ANN) in predicting tasks. For the problem setting, we consider the next day closing price of four major banks: two Vietnamese banks—Vietcombank (VCB), and BIDV (BID), and two German banks—Deutsche Bank (DBK.DE), and Commerzbank (CBK.DE). Data of High, Low, Open and Close prices of each stock are used to construct a new set of explanatory variables to be input into the machine learning models. The predictive performance of each model on each stock is then evaluated using three metrics: the Root Mean Squared Error (RMSE), the Mean Absolute Percentage Error (MAPE), and the Mean Bias Error (MBE).