Stock Price Prediction Application using Multiple Regression Model
HANUMANNA GARI ARAVIND
, Dr. VARADARAJU H R , POORNA PRAGNA H , RAKSHITHA C S , VANTIKONDA NARESH CHANDRA
1. Stock Price Prediction 2. Machine Learning 3. Multiple Regression 4. LSTM (Long Short-Term Memory) 5. Predictive Analytics
The "Stock Price Prediction System Application" leverages machine learning techniques to forecast future stock prices, assisting investors in making well-informed decisions. By analyzing historical stock data, market trends, and economic factors, the system follows a structured process that includes data collection, preprocessingfeature extraction, training of the model, and assessment. The primary algorithm used is multiple regression, which establishes relationships between past and future price movements. Model Metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and R-squared (R2) are used to evaluate performance. The system may incorporate more sophisticated machine learning models, such decision trees, support vector machines (SVM), and deep learning, to improve predicted accuracy. models like Long Short-Term Memory (LSTM) networks. In addition to forecasting stock prices, the system aims to incorporate real-time data, financial news sentiment analysis, and risk assessment models to further improve predictions. Future developments could involve integrating external factors like geopolitical events and investor sentiment to refine decision-making. This application bridges the gap between finance and data science, providing investors with data- driven insights that reduce uncertainty and enhance investment strategies through predictive analytics. The project not only demonstrates machine learning's potentialin finance but also creates a platform for further advancements in AI- based market forecasting.
"Stock Price Prediction Application using Multiple Regression Model", TIJER - TIJER - INTERNATIONAL RESEARCH JOURNAL (www.TIJER.org), ISSN:2349-9249, Vol.12, Issue 4, page no.a11-a17, April-2025, Available :https://tijer.org/TIJER/papers/TIJER2504003.pdf
Volume 12
Issue 4,
April-2025
Pages : a11-a17
Paper Reg. ID: TIJER_157226
Published Paper Id: TIJER2504003
Downloads: 000280
Research Area: Science and Technology
Country: chickballapur, Karnataka, India
ISSN: 2349-9249 | IMPACT FACTOR: 8.57 Calculated By Google Scholar | ESTD YEAR: 2014
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.57 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: TIJER (IJ Publication) Janvi Wave
