Test Case Optimization Through Ant Colony Optimization Enabled Boosted Regression Model

The avalanche of data creates complex operational issues in real world scenarios. In terms of making the test procedures simple and effective test case optimization techniques are applied. To achieve better test case performance, the proposed system focused on creating a model centric method that comparatively overheads the test case optimization works. The presented system considers the comparative evaluation of test case optimization of MIS dataset. The methods such as Linear regression (LR), Customized Random Forest regression (RFR), the robust Gradient boost regression (GBR), dynamically working Support vector machine (SVM) and proposed Ant colony optimized Boosted regression model (ACO-BRM). The proposed approach exposed to the benefit of nature inspired optimization model named ant colony and optimized the test cases with boosted regression model and achieved the minimum of mean absolute error of 0.34 comparatively with existing state of art approaches. The priority score is enhanced after the optimization process.