Connection of the distributed generators (DGs), poses new challenges for operation and management of the distribution system. An important issue is that of islanding, where a part of the system gets disconnected from the DG. This thesis explores the use of several data-mining, and machine learning techniques to detect islanding. Several cases of islanding and non- islanding are simulated with a standard test-case: the IEEE 13 bus test distribution system. Different types of DGs are connected to the system and disturbances are introduced. Several classifiers are tested for their effectiveness in identifying islanded conditions under different scenarios. The simulation results show that the random forest classifier consistently outperforms the other methods for a diverse set of operating conditions, within an acceptable time after the onset of islanding. These results strengthen the case for machine-driven based tools for quick and accurate detection of islanding in microgrids.