A new method called Weighted Support Vector Regression (WSVR) was developed to improve the accuracy of predicting outcomes based on data. By assigning different weights to each data point, the model reduces errors caused by outliers and noise. The approach involves calculating the distance of each data point from the center of a specific shape in the data space. When tested on a simulated dataset, WSVR outperformed traditional Support Vector Regression (SVR) in terms of accuracy and error reduction.