High energy cosmic neutrinos interacting in ice will induce a particle cascade. The Radar Echo Telescope (RET) aims to detect the neutrino through probing the cascade by means of the radar echo method. In order to study this process, we simulate transmitting a radio signal to scatter off the cascade. A return radio signal will be detected at a number of user-defined receivers. Several properties in the radio signals have been observed when systematically varying the direction of the cascade, such as patterns in the intensity and fourier transform amplitudes at half, at and twice the transmit frequency. Given these patterns, it is possible to train machine-learning algorithms to reconstruct the cascade direction. As such, we simulate a simple setup of four receivers and vary the direction of the cascade, keeping the position and energy constant, and show the reconstruction accuracy that can be currently achieved.