The economic value of Chinese liquor is closely related with its age. Results from gas chromatograph (GC) analysis indicated that 8 dominant compounds were decreased with the increase of liquor age (0 to 5 years) while ethyl lactate was found to be the most stable dominant compound as no significant change was observed in it during the aging process. Liquor groups with different ages were well-discriminated by principal component analysis (PCA) based on electronic nose signals. High-accurate identification of liquor ages was realized using linear discriminant analysis (LDA) with the accuracy of 98.3% of the total 120 samples from six age groups. Partial least squares regression (PLSR) exhibited satisfying ability for liquor age prediction (R2: 0.9732 in calibration set and 0.9101 in validation set). The feasibility of volatile compounds prediction using PLSR combined with electronic nose was also verified by this research. However, the accuracies of PLSR models can be further promoted in future researches, perhaps by using more suitable sensors or modeling approaches.