Rheumatoid Arthritis (RA) is a chronic, immune-mediated inflammatory disease. It primarily affects the joints. It causes significant morbidity and disability. Understanding the genetic and molecular interactions in RA is crucial for early diagnosis and treatment. This research analyzes genetic variants and expression quantitative trait loci (eQTLs) in RA using statistical and machine learning techniques. Genetic variants impact gene expression and are critical in understanding RA mechanisms. The Rheumatoid Arthritis Bioinformatics Centre (RABC) eQTL dataset contains 119,816 rows and 17 columns. Significant genetic variants were identified using Bonferroni and Benjamini–Hochberg corrections. Subsampling confirmed the robustness of findings. Hierarchical clustering revealed distinct gene feature groupings. Random Forest and Extra Trees classification models showed high accuracy and efficiency. Extra Trees Regressor demonstrated high R-squared values and low execution times. These models provide valuable tools for genetic studies in RA. The analysis of the eQTL dataset revealed significant tissue-specific variations. The Heart Left Ventricle has the highest eQTL count. The research emphasizes the importance of robust analytical methods for complex genetic data. Future research should explore the functional implications of eQTLs in RA pathogenesis. Expanding the dataset to include diverse populations may enhance generalizability. Advanced machine learning models could improve predictive performance.