In this paper, the authors have proposed a new prediction-based location management scheme for cellular networks. The current mobile switching centre predicts the previous mobile switching center of user, and then imports the data about the mobile terminal from that. For this purpose it uses a prediction table, which is based on the neighboring location areas. The analytical model and formulation presents the conceptual schema of proposed scheme. The performance comparisons and numerical analysis is helpful to find out the efficiency and effectiveness of the proposed system, with respect to existing location management techniques. It has been observed that, the registration cost, and the network overhead at mobile switching center have been reduced in the proposed prediction-based scheme.