Software Quality is one of the biggest assets in the Software development process. Any projects success or failure is dependent on the Software Quality. Software Quality can be assured through various phases of testing [1]. Testing techniques like alpha-beta testing, Black box testing and White box testing techniques can assure the software quality to a certain level. Faults can be predicted and rectified by these techniques. Manually testing can be very expensive and sometime impossible to perform testing. An automated hybrid software fault prediction model that is capable to measure the relative quality of software and identify their faulty components can significantly reduce software development effort and the threat of software project failure. In our paper we used a hybrid algorithm using ANN(Artificial Neural Networks) Wrapper and FISHER Filter techniques.