Table 4. Results of all machine learning and deep learning models on both of our datasets of the best-performing model during the hyperparameter study. For all models, we report MAE, MSE, and RMSE of the respective 5-fold cross-validation. Best values are highlighted in bold. Model Matches included Matches excluded Mean Absolute Error Mean Squared Error Root Mean Squared Error Mean Absolute Error Mean Squared Error Root Mean Squared Error KNeighbors 1.29 (±0.02) 3.81 (±0.09) 1.95 (±0.02) 1.21 (±0.01) 3.5 (±0.04) 1.87 (±0.01) Ridge 1.29 (±0.02) 3.81 (±0.09) 1.95 (±0.02) 1.21 (±0.01) 3.5 (±0.04) 1.87 (±0.01) Lasso 2.5 (±0.01) 8.25 (±0.07) 2.87 (±0.01) 2.5 (±0.03) 8.25 (±0.15) 2.87 (±0.03) ElasticNet 2.5 (±0.01) 8.25 (±0.07) 2.87 (V0.01) 2.5 (±0.03) 8.25 (±0.15) 2.87 (±0.03) Decision Tree 1.7 (±0.04) 7.71 (±0.28) 2.78 (±0.05) 1.54 (±0.04) 6.85 (±0.25) 2.62 (±0.05) ExtraTree 1.25 (±0.01) 3.05 (±0.05) 1.75 (±0.01) 1.15 (±0.03) 2.65 (±0.12) 1.63 (±0.04) Random Forest 1.47 (±0.01) 3.52 (V0.06) 1.88 (±0.02) 1.37 (±0.02) 3.12 (±0.11) 1.77 (±0.03) Gradient Boosting 2.36 (±0.01) 7.58 (±0.08) 2.75 (±0.02) 2.35 (±0.02) 7.54 (±0.12) 2.74 (±0.02) AdaBoost 2.4 (±0.02) 7.65 (±0.08) 2.77 (±0.01) 2.39 (±0.03) 7.54 (±0.13) 2.75 (±0.02) DL 1.21 (±0.01) 3.47 (±0.07) 1.86 (±0.01) 1.04 (±0.07) 2.70 (±0.23) 1.64 (±0.05)