STOCK MARKET PRICE PREDICTION USING ARTIFICIAL INTELLIGENCE TECHNIQUES

Main Article Content

Hamza Nadim Shaikh
B. Pruthviraj Goud

Abstract

Predicting stock prices is a challenging task due to the inherent volatility and non-linearity of financial markets. This study explores the application of Support Vector Machine (SVM) with an RBF kernel and XGBoost for forecasting future stock price movements using historical data encoded as ordinal values. The SVM model demonstrated strong performance with an R-squared value of 0.968, low Mean Squared Error (MSE), and Mean Absolute Error (MAE), making it a reliable and stable approach for consistent predictions. Conversely, XGBoost achieved a higher R-squared value of 0.998, indicating superior trend-capturing ability but exhibited higher MSE, suggesting a tendency to overfit. Visualization of model performance revealed that XGBoost excels in capturing short-term price fluctuations, while SVM offers greater consistency with fewer errors. The hybridization of Support Vector Regression (SVR) with SVM is proposed to achieve optimal results, balancing predictability and stability. This study highlights the hybrid model using LSTM to learn patterns to predict the price with SVR with the strong decision making using SVM.

Downloads

Download data is not yet available.

Article Details

Section
Articles
Author Biography

Hamza Nadim Shaikh

Department of Information Technology,

Anurag University,

Hyderabad