A method (200) for determining future resource requirements in a given location, the method comprising the steps of obtaining (110) transaction data, the transaction data indicative of past resource use at a given location. At least one model may be trained (120) based on a set of parameters by determining (121) a distribution associated with the transaction data; and generating (122) a kernel based on the distribution and the set parameters, the kernel being arranged to output an estimated distribution. The kernel is refined (123) and validated (124) based on a comparison between the distribution and the estimated distribution. A density map is then generated (125) based on the at least one trained model. The density map is then sent (130) to a control system for determining future resource requirements in the given location.