With the advent of artificial intelligence (AI) and its subfield, machine learning (ML), there has been a transformation in healthcare research. The applications of AI/ML have expanded from retrieving useful insights from high-throughput data, categorizing patients, improving disease diagnosis, and clinical laboratory testing to treatment selection. In cancer, targeted therapy proves to be a better remedy compared to conventional chemotherapy and radiation therapy. Target therapy offers personalized treatment to cancer patients by effectively targeting the cancer cells and sparing the normal ones. The knowledge of genetic interaction (GI) has been utilized in the targeted therapy approach. Genetic interactions are the phenotypic outcomes resulting from two or more gene interactions. Genetic interactions such as synthetic lethality and synthetic viability explain the phenomenon of drug sensitivity and resistance, respectively. Several strategies have been employed for the identification of synthetic lethal pairs. The chapter primarily discusses some machine learning models that predict synthetic lethal interactions and summarizes the advantages and disadvantages of these classifiers. R-based step-by-step protocols have been shown for executing two ML-based synthetic lethal interaction prediction algorithms. By the end of the chapter, the readers would understand the role of genetic interactions in cancer and be able to execute machine learning models to predict synthetic lethal interactions.