A Method for Determining the Accuracy of Stock Prices using Gradient Boosting and the Support Vector Machines Algorithm

The intention of work is to detect accuracy in stock price prediction based on stock values. Materials and Methods: Gradient Boosting Machines (GBM) Algorithm with sample size = 20 and Support Vector Machine (SVM) Algorithm with sample size = 20 was iterated at different times for envisagingaccurateness of stock prices. The Novel Loss procedure used in Gradient Boosting Machines Algorithm depends upon previous stock values which help to minimize overall prediction error. Results: Gradient Boosting Algorithm has ominously better accuracy (92.3 %) compared to SVM Algorithm accuracy (76%) with significance value p=0.00 (2 tailed). Conclusion: GBM algorithm with Novel loss function helps in envisaging with more accuracy the percentage of stock values.