Feature extraction is a crucial step in the classification process, especially when dealing with high-dimensional data. It involves transforming raw input data into a reduced, more informative representation, aiming to capture essential patterns and discard irrelevant or redundant information. In this research work recursive feature elimination (RFE) feature extraction method was being deployed. The main objective of the research work was to measure the impact of recursive feature elimination (RFE) method in improving the accuracy and other performance measures of software defect predication models. The experimental setup was being established using Python libraries. Finally, the findings suggest that proposed RFE method was better than the existing feature selection methods.