Enhancing Predictive Analytics Through Hybrid Machine Learning Models: A Comparative Analysis Of SVM-NB And Lasso-Ridge Techniques
A. Sheik Abdullah, Utkarsh Mishra, K Akash, Athul Ravi, S P Mohan Arvind · 2024
During the moment of data-driven decision-making, effective classification algorithms play a major part in different areas. This study showcases a comparative analysis of Support Vector Machines (SVM) and Naïve Bayes (NB), two standout machine learning systems, through various data sets. We suggest a unique hybrid method that cleverly blends SVM and NB, tackling their separate inadequacies while leveraging their strengths. Likewise, we present a hybrid model that combines lasso and ridge regression methods for improved performance. Our experimental outcomes reveal the superior predictive accuracy of the proposed SVM-NB hybrids over singular algorithms and the Lasso-Ridge Hybrid. This research highlights the potential of hybrid methods in advancing predictive analytics, providing a hopeful path for optimizing classification duties in practical situations.