Immune microenvironment is implicated in cancer progression. However, the role of immune microenvironment in bladder cancer has not been fully explored. Open-accessed datasets GSE120736, GSE128959, GSE13507, GSE31684, GSE32548, GSE48075, GSE83586, and The Cancer Genome Atlas (TCGA) database were enrolled in our study. Single-sample gene set enrichment analysis (ssGSEA) was used to quantify 53 immune terms in combined BLCA cohorts. The top 10 important immune terms were identified through random forest algorithm for model establishment. Our model showed satisfactory efficacy in prognosis prediction. Furthermore, we explored clinical and genomic feature differences between high- and low-risk groups. The results indicated that the patients in the high-risk group might be associated with worse clinical features. Gene set enrichment analysis showed that epithelial–mesenchymal translational, mTORC1 signaling, mitotic spindle, glycolysis, E2F target, and G2M checkpoint pathways were aberrantly activated in high-risk patients, partially explaining its worse prognosis. Patients in the low-risk group showed better immunotherapy response according to TIDE and TCIA analysis, indicating that our model could effectively predict the immunotherapy response rate. KCNH4, UGT1A1, TPO, SHANK1, PITX3, MYH1, MYH13, KRT3, DEC1, and OBP2A genes were identified as feature genes in the high- and low-risk patients. CMAP analysis was performed to identify potential compounds targeting the riskscore.