Abstract—Renal Cell Carcinoma (RCC) is one of the most common malignancy and the sixth cause of leading death from the cancer. In this study, our aim is to identify biomarker candidates expressed at different levels between subtypes of RCC for potential new therapy for RCC. A total of 1,020 raw RNA-Seq counts of renal cancer dataset including 606 KIRP, 323 KIRC and 91 KICH were obtained from the Cancer Genome Atlas (TCGA) Project. Five statistical learning methods including support vector machines (SVM), random forests (RF), penalized discriminant analysis (PDA), naïve bayes (NB) and k-nearest neighbors (KNN) were applied on the purpose of classification. Gene ontology (GO) and Kyoto encyclopaedia of genes and genomes (KEGG) pathway analysis were also conducted for a deeper understanding of differentially expressed genes in three renal cancer subtypes. We identified 181 up-regulated and 69 down-regulated genes that showed a significant differential expression between cancer samples. Classification analysis resulted that integrating these genes in a statistical learning framework perform between 90.7-94.6% accuracy, 81.4-91.2% sensitivity and 92.9-97.0% specificity. Our findings showed a few DEGs including NPK, HRNPLT, ARF1 and TTR might contain a critical role in RCC. Furthermore, study demonstrated using the DEGs as the high rate hit distinguish and classification for RCC subtypes.