In this master thesis, a study was conducted on a method known as Dynamic mode decomposition(DMD), an equation-free technique which does not require to know the underlying governing equations of the complex data. As a result of massive datasets from various resources, like experiments, simulation, historical records, etc. has led to an increasing demand for an efficient method for data mining and analysis techniques. The main goals of data mining are the description and prediction. Description involves finding patterns in the data and prediction involves predicting the system dynamics. An important aspect when analyzing an algorithm is testing. In this work, DMD-a data based technique is used to test different cases to find the underlying patterns, predict the system dynamics and for reconstruction of original data. Using real data for analyzing a new algorithm may not be appropriate due to lack of knowledge of the algorithm performance in various cases. So, testing is done on synthetic data for all the cases discussed in this work, as it is useful for visualization and to find the robustness of the new algorithm. Finally, this work makes an attempts to understand the DMD's performance and limitations better for the future applications with real data.