Mobile Location Management (MLM) is an important and complex telecommunication problem found in mobile cellular GSM networks. Basically, this problem consists in optimizing the number and location of paging cells to find the lowest location management cost. There is a need to develop techniques capable of operating with this complexity and used to solve a wide range of location management scenarios. Nature inspired algorithms are useful in this context since they have proved to be able to manage large combinatorial search spaces efficiently. The aim of this study is to assess the performance of two different nature inspired algorithms when tackling this problem. The first technique is a recent version of Particle Swarm Optimization based on geometric ideas. This approach is customized for the MLM problem by using the concept of Hamming spaces. The second algorithm consists of a combination of the Hopfield Neural Network coupled with a Ball Dropping technique. The location management cost of a network is embedded into the parameters of the Hopfield Neural Network. Both algorithms are evaluated and compared using a series of test instances based on realistic scenarios. The results are very encouraging for current applications, and show that the proposed techniques outperform existing methods in the literature.