This research aims to highlight the usage of regression techniques, which is one of the key concepts in machine learning, to predict student's exam score based on various predictor variables and determine the best model. Moreover, evaluation metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R²) will also be shown. The 16 regression techniques include XGB Regression, Random Forest Regression, Gradient Boosting Regression, Extra Trees Regression. KNeighbors Regression, Linear Regression, Lasso, LGBM Regressor, Ridge, Support Vector Regression (SVR), ElasticNet, Decision Tree Regression, Huber Regression, Bayesian Ridge, Multi-layer Perceptron (MLP) Regression and Neural Network Regression (NNR). Each test was implemented using a dataset from Kaggle, which contains over 6000 rows, pre-trained models from scikit-learn and other Python libraries such as pandas, numpy and tensorflow.