This thesis is to study the distribution system loss by applying artificial neural networks(ANN). To enhance the efficiency of loss analysis, the distribution system network has been obtained by retrieving that component information for the automated mapping and facility management system (AM/FM). The topology process and node reduction has also been applied to identify the network configuration and the input data for load flow analysis. The load survey study is used to derive the typical load patterns of various customer losses. The monthly energy consumption of customers by each transformer, which has been retrieved for the customer information system(CIS), is used to derive the hourly loading of each distribution transformer. The three phase load flow analysis has been performed for different types of distribution feeders to solve feeder loss to generate the data set for the training and testing of neural networks. The ANN for distribution loss analysis, which has been obtained after network training, can solve the distribution system loss very efficiently according to the feeder load demand, length, transformer capacity and voltage level. With short feeder length and voluminous customers served by the distribution feeders in urban area, the transformer core loss and secondary line loss contribute most of the distribution feeder loss. On the other hand, the line loss of rural distribution feeder is more significant because of the longer distribution lines to serve more scattering customers. With the neural based distribution system loss modeling, the distribution system loss can be estimated very easily, which can provide Taipower a good reference to enhance the operation efficiency of distribution system.