It is well-established that certain phenotypic outcomes result from interactions between multiple genes rather than being attributable to individual genes. Mapping all possible gene combinations to study genetic interactions is challenging with low-throughput experimental assays. While CRISPR screening has provided a high-throughput approach for mapping genetic interactions, CRISPR screen data are limited by data quality, technical challenges, and the limitations of current tools. Furthermore, CRISPR screens primarily focus on phenotypic outcomes and additional methods based on transcriptomics and gene dependency failed to identify previously validated genetic interactions.The first aim focuses on enhancing the identification of genetic interactions. Rather than relying solely on expected and observed phenotypes, it used Random Forest model to integrate multiple data types. The model was trained on experimentally validated gene pairs and the model outperformed CRISPR-based method, dependency method, and RNA expression-based approaches in identifying validated genetic interactions. This underscores the value of integrating diverse datasets and utilizing random forests to improve the identification of genetic interactions. The second aim is to predict genetic interactions using predictive features from available databases. Analysis showed that the a-score (co-expression) and p-score (co-occurrence across organisms) from the STRING database were the most predictive. These features trained a random forest classifier on experimentally validated genetic interaction pairs. The classifier's test set showed a high overlap with validated pairs, providing a reference set of gene pairs likely to be genetic interactions, which can be further validated through low-throughput experiments or CRISPR screens.