Talent flow analysis is a process for analyzing and modeling the flows of employees into and out of targeted organizations, regions, or industries. A clear understanding of talent flows is critical for many applications, such as human resource planning and brain drain monitoring. However, existing studies on talent flow analysis are either qualitative or limited by coarse level quantitative modeling. In this paper, we provide a data-driven approach to model the dynamics of talent flows by leveraging the rich information in Job Transition Networks (JTN). Specifically, we investigate how to enrich the sparse talent flow data by exploiting the correlations between the stock price movement and the talent flows. Then we formalize the modeling problem as to predict the increments of the edge weights in the dynamic JTNs. In this way, the problem is transformed into a multi-step sequence forecasting problem. A deep sequence prediction model is developed based on the recurrent neural network model, which consumes multiple input sources derived from dynamic JTNs. Experimental results on real-world data show that the proposed model outperforms other benchmarks. The results also indicate that the proposed model provides reasonable performance when the historical talent flow data are not completely available.