This paper presents a systematic and bibliometric literature review on hybrid methods that combine optimization and machine learning techniques for clustering and classification. The authors aim to identify the potential of these hybrid methods to overcome the limitations of both individual methodologies. The review covers a wide range of topics, including the evolution of optimization and machine learning methods, the characteristics of each methodology, and the integration of their strengths to enhance performance. The paper also includes a numerical overview of the literature published since 1970 and an in-depth analysis of the last three years. Additionally, a SWOT analysis of the ten most cited algorithms is performed to evaluate their strengths, weaknesses, opportunities, and threats. The study highlights the most notable works and discoveries in hybrid methods for clustering and classification, as well as the difficulties of pure methods that can be addressed through hybrid approaches. The paper concludes by summarizing the main results and proposing future research directions.This paper presents a systematic and bibliometric literature review on hybrid methods that combine optimization and machine learning techniques for clustering and classification. The authors aim to identify the potential of these hybrid methods to overcome the limitations of both individual methodologies. The review covers a wide range of topics, including the evolution of optimization and machine learning methods, the characteristics of each methodology, and the integration of their strengths to enhance performance. The paper also includes a numerical overview of the literature published since 1970 and an in-depth analysis of the last three years. Additionally, a SWOT analysis of the ten most cited algorithms is performed to evaluate their strengths, weaknesses, opportunities, and threats. The study highlights the most notable works and discoveries in hybrid methods for clustering and classification, as well as the difficulties of pure methods that can be addressed through hybrid approaches. The paper concludes by summarizing the main results and proposing future research directions.