Resting-state functional magnetic resonance imaging (rs-fMRI) offers the opportunity to delineate individual-specific brainnetworks. A major question is whether individual-specific network topography (i.e., location and spatial arrangement) isbehaviorally relevant. Here, we propose a multi-session hierarchical Bayesian model (MS-HBM) for estimating individual-specific cortical networks and investigate whether individual-specific network topography can predict human behavior.The multiple layers of the MS-HBM explicitly differentiate intra-subject (within-subject) from inter-subject (between-subject)network variability. By ignoring intra-subject variability, previous network mappings might confuse intra-subject variabilityfor inter-subject differences. Compared with other approaches, MS-HBM parcellations generalized better to new rs-fMRI andtask-fMRI data from the same subjects. More specifically, MS-HBM parcellations estimated from a single rs-fMRI session(10 min) showed comparable generalizability as parcellations estimated by 2 state-of-the-art methods using 5 sessions(50 min). We also showed that behavioral phenotypes across cognition, personality, and emotion could be predicted byindividual-specific network topography with modest accuracy, comparable to previous reports predicting phenotypes basedon connectivity strength. Network topography estimated by MS-HBM was more effective for behavioral prediction thannetwork size, as well as network topography estimated by other parcellation approaches. Thus, similar to connectivitystrength, individual-specific networktopographymight also serve as afingerprint of human behavior.