TY - CONF

T1 - TimeHorizon Stock Market Price Prediction

AU - Raj, Nikhil

AU - Menon, Parth Krishnan B

AU - P, Sidharth

AU - Venugopalan, Anand

AU - K, Sreeshma

AU - Vadkeppattu, V K

N1 - Conference code: 16

PY - 2025

Y1 - 2025

N2 - Forecasting of stock market is a way to predict future prices of stocks. It is a longtime attractive topic for researcher and investors from its existence. The Stock prices are dynamic day by day, so it is hard to decide what is the best time to buy and sell stocks. This is a work for prediction of stock market prices for both short-term and long-term investors seeking early recommendations and used in need of financial distress warnings. The work explores the application of various machine learning algorithms including Linear regression, Random Forest, and Support Vector Regression, to forecast stock market prices in the stock market. From these, machine learning algorithms are trained and evaluated for each model's performance using metrics such as accuracy, precision score etc. The finding showcased that efficiency of Support Vector Machines (SVM) and Random Forest has accurately predicted stock market values. The proposed model is SVM-ICA fusion model combining SVM and independent component analysis (ICA). The system was found to achieve an accuracy of 60% using random forest, trained on an average of 1000 data values The proposed model aims to provide forecasting on future stock prices, providing investors with insights on informed decision-making. Additionally, the practical implications of our work also depict the applications in algorithmic trading, risk management and optimization.

AB - Forecasting of stock market is a way to predict future prices of stocks. It is a longtime attractive topic for researcher and investors from its existence. The Stock prices are dynamic day by day, so it is hard to decide what is the best time to buy and sell stocks. This is a work for prediction of stock market prices for both short-term and long-term investors seeking early recommendations and used in need of financial distress warnings. The work explores the application of various machine learning algorithms including Linear regression, Random Forest, and Support Vector Regression, to forecast stock market prices in the stock market. From these, machine learning algorithms are trained and evaluated for each model's performance using metrics such as accuracy, precision score etc. The finding showcased that efficiency of Support Vector Machines (SVM) and Random Forest has accurately predicted stock market values. The proposed model is SVM-ICA fusion model combining SVM and independent component analysis (ICA). The system was found to achieve an accuracy of 60% using random forest, trained on an average of 1000 data values The proposed model aims to provide forecasting on future stock prices, providing investors with insights on informed decision-making. Additionally, the practical implications of our work also depict the applications in algorithmic trading, risk management and optimization.

KW - National Stock Exchange (NSE)

KW - Support Vector Regression (SVM)

KW - Random Forest

KW - Stock Market

KW - Root Mean Square Error (RMSE)

KW - Feature Engineering

KW - Support Vector Machine and Independent component analysis (SVM-ICA)

UR - https://www.scopus.com/pages/publications/105034223287

M3 - Abstract

T2 - 16th International Conference on Advances in Computing, Control, and Telecommunication Technologies

Y2 - 25 June 2025 through 26 June 2025

ER -