Search-Based Software Engineering (SBSE) is one of the techniques used for software defect prediction (SDP), in which search-based optimization al-gorithms are used to identify the optimal solution to construct a prediction model. As we know, the ranking methods of SBSE are used to solve insufficient sample problems, and the feature selection approaches of SBSE are employed to enhance the prediction model's performance with curse-of-dimensionality or class imbal-ance problems. However, it is ignored that there may be a complex problem in the process of building prediction models consisting of the above problems. To address the complex problem, two multi-objective learning-to-rank methods are proposed, which are used to search for the optimal linear classifier model and reduce redun-dant and irrelevant features. To evaluate the performance of the proposed methods, excessive experiments have been conducted on 11 software programs selected from the NASA repository and AEEEM repository. Friedman's rank test results show that the proposed method using NSGA-II outperforms other state-of-the-art single-objective methods for software defect prediction.