ENHANCING PREDICTIVE ACCURACY WITH ROBUST LIU AND RANDOM FOREST REGRESSION

Robust and Random Forest regression procedures are powerful machine learning algorithms that enhance predictive accuracy and handle complex datasets with diverse characteristics. The Robust Liu regression algorithm is designed to address the limitations of conventional regression methods. The robust Liu regression method is considered more reliable in the presence of outliers and multicollinearity. On the other hand, Random Forest is an ensemble learning method that constructs multiple decision trees to improve classification and regression tasks by aggregating predictions from individual trees, thereby mitigating overfitting and increasing robustness to noise. Its ability to capture nonlinear relationships and handle high-dimensional data makes it suitable for many real-world applications. This study compares the performance of Least Squares, Liu, Robust Liu, and Random Forest regression methods using prediction error measures in real and simulated environments. This synergy offers new possibilities for researchers to improve prediction accuracy in the presence of heterogeneous non-normal, multicollinear data and outliers.