Aim: This following research compares the Novel Support Vector Machine Algorithm and the K-Nearest Neighbor Algorithm for stock price prediction optimization in order to enhance the Accuracy of real-time stock exchange. Materials and Methods: To optimize the pH, the Novel Support Vector Machine Algorithm (N=10) and K-Nearest Neighbor (N=10) are simulated by adjusting the Novel Support Vector Machine parameters and K-Nearest Neighbor parameters. Gpower 80 percent is utilized to compute sample size for two groups, and 20 samples are investigated in this research. Results: Utilizing SPSS Software, an independent sample size is used to evaluate the accuracy rate. Although Support Vector Machine generates 84.67 percent accuracy, KNN produces 47.87 percent accuracy. The difference in statistical significance between Novel Support Vector Machine and KNN was discovered to be 0.508 (p<0.05). Conclusion: In terms of accuracy, the Support Vector Machine algorithm outperforms the K-Nearest Neighbor algorithm.