The aim of this study was to identify a microRNA (miRNA) expression signature for predicting HCC (hepatocellular carcinoma) survival. A total of 322 HCC patients in The Cancer Genome Atlas (TCGA) database were randomly divided into training and testing set. miRNAs, associated with survival time in the training set, were identified by using univariate Cox regression analysis. The risk score was formulated based on the expression levels of these miRNAs. Then the miRNA signature was validated in testing set through Kaplan–Meier analysis and log‐rank test. hsa‐miR‐301a, hsa‐miR‐132, hsa‐miR‐212, hsa‐miR‐489, and hsa‐miR‐1468 were identified to formulate risk score in training set and used to calculate the risk score of each patients in testing set. About 161 patients in testing set were segregated into high‐ and low‐risk group according to the median risk score. The survival time of high‐risk group was significantly shorter (p = 0.0248) than low‐risk group in testing test. The target genes of five miRNAs were significantly enriched in valine, leucine, and isoleucine degradation pathway and PPAR signaling pathway. hsa‐miR‐1468 had an up‐regulated tendency in HCC tissues compared to adjacent tumor tissues. The expression of hsa‐miR‐301a, hsa‐miR‐132, hsa‐miR‐212, hsa‐miR‐489, and hsa‐miR‐1468, which might be potential biomarkers to evaluate HCC patients' prognosis.