Swagnik Dey & Mayukh Paul
Computer Science
December 2024
Aim:This research work aims at finding how ML models are used for the short-term prediction of stock market based on how past data is used for forecasting patterns of stock price movements..Purpose:The purpose of this research is to compare different machine learning techniques for the prediction of stock price movements. Techniques used include Logistic Regression, Bayesian Networks, Support Vector Machines with radial basis kernels, and Stochastic Neural Networks. Technical indicators will also be discussed on how they impact prediction accuracy.Method:The study collected historical stock market data on 80 NYSE stocks using the Alpha Vantage API, thus capturing open, high, low, close prices, volume, and other time-series data. A total of 20 predictors, incorporating 15 commonly used technical indicators, were used for training the models. Models were evaluated based on criteria such as mean squared error MSE and prediction accuracy. It utilized different methods of machine learning and emphasized predicting the trend of stock prices.Results:The preliminary results of the
315- 328
© Airo Journals 2021
