The Automated Teller Machine (ATM) is needed when users need immediate banking transactions. But sometimes ATM has some problems such as ATMs are being broken, money deposited in ATM depleted, the number of people who queued at ATM, etc. At that time, people needed an alternative ATM located nearby. To make the process of ATM search easier, than it takes a system that serves to find the nearest ATM from the ATM location that the user is visiting. Padang Sidempuan City has many ATMs in various places. This research will make the nearest ATM search system in Padang Sidempuan city. In this system, there is a menu to search by selecting the starting point and ATM of the bank that you want to go and will produce the nearest ATM and the line from the starting point to the ATM. To support the closest ATM search in this system, the deep first search algorithm and the greedy algorithm applied to this system. Then, the performance of both algorithms will be compared based on process time and distance. After implementation and comparison, it is known that the complexity of the depth-first search algorithm is the same as the complexity of the algorithm greedy, (N2). Attesting with a sample of 10 starting points and 1 ATM destination, the depthfirst search algorithm has an average running time of 239.9675 milliseconds, and the average distance is 3033.555 meters, while a greedy algorithm has an average running time of 274.8501 milliseconds and the average distance is 2035.2568 meters. So it concludes that the depth-first search algorithm is more efficient in running time than the greedy algorithm. But in generating shorter distances, the greedy algorithm is better than the depth-first search algorithm.