Abstract: The technique of ordering the test cases in the test suite in order to enhance the effectiveness of testing process is known as the test case prioritization. According to some criterion the test cases are accomplished in an order that are having the maximum priority than the one with lower priority by using the prioritization technique. This prioritization technique will be employed to sort the test cases in an order. This in turn increases the rate of fault detection. The measure to detect the fault rate increases will improves the performance of the running system and the makes the software testing process an efficient one. There may be a problem of occurrence of faults due to some error in coding. Hence, it is necessary to detect the fault rate to make the system an efficient one. In this proposed work an input test case dataset are preprocessed followed by the generation of Adjacency Matrix (AM). The features are then extracted by the use of adjacency matrix. A novel Density Based Spatial Clustering of Application with Noise (DBSCAN) is presented from which the optimization of test case using the Feed Forward Neural Network (FFNN) is carried out to obtain the optimized results. Then the faults in the test case are predicted which is then prioritized according to the maximization of test case with the help of bubble sort algorithm. This in turn sorts the test case and swaps them as per the priority provided for the test case. The performance analysis was made for the proposed system (NDBSC-FFNN) and are compared with the existing methodologies. From, this analysis it is clear that the proposed method performs well than the existing methodologies.